A computer-implemented method for estimating evapotranspiration of a sculpted landscape and an irrigation system

Abstract

Disclosed herein is a computer-implemented method for estimating evapotranspiration of a sculpted landscape, such as a golf course, wherein the sculpted landscape comprises a surface and one or more objects, such as buildings or trees. Further 5 disclosed is determining an estimated irrigation value and controlling an irrigation device to apply water corresponding to estimated irrigation value and an irrigation system comprising an irrigation device and a control unit configured to carry out these steps. Further disclosed is a computer program product comprising instructions, which when executed by a computer, cause the computer to carry out the steps of the method.

Description

[0001] Title

[0002] A computer-implemented method for estimating evapotranspiration of a sculpted landscape and an irrigation system

[0003] Technical Field

[0004] The present disclosure is related to a computer-implemented method for estimating evapotranspiration of a sculpted landscape, such as a golf-course, an irrigation system, a computer program product, and a computer-readable data carrier thereof.

[0005] Background

[0006] Irrigation is a cornerstone of sustainable agricultural and turf management practices, especially in regions where water resources are scarce or unevenly distributed. Particularly, in sculpted landscapes, such as golf courses, or tennis courts, that are meticulously and artificially designed, maintaining optimal turf conditions is essential for ensuring the quality and fairness of play. Maintenance of a sculpted landscape is, however, a complex task due to e.g. variable topographies that create an uneven water distribution, local temperature differences, and a diverse type of turf species that can be affected differently by seasonal change, disease pressure or even weather uncertainty.

[0007] One type of maintenance which is generally needed for such sculpted landscapes is irrigation. For instance, for irrigation, field crop irrigation management typically requires frequent decisions based on plant water demand. Recommendations are usually derived from a reference evapotranspiration (ET0) estimate, typically calculated using the standard Penman-Monteith equation. This equation relates plant traits and weather factors to water loss through evapotranspiration. Since plant characteristics vary by species and growth stage, crop evapotranspiration (ETc) is also typically calculated by adjusting the reference crop ET0 using crop-specific coefficients by ETc= Kc*ET0.

[0008] For instance, US2021360885 A1 discloses systems and methods for providing crop coefficient (Kc) values, including near real time and forecast values for the management of precise agricultural irrigation, as well as data collection for monitoring and refining the evapotranspiration calculations. However, these existing models typically generalize evapotranspiration ET estimations across large areas, leading to discrepancies in water application and turf canopy health outcomes. Furthermore, current irrigation systems often rely on manual operations or simplistic automations, lacking integration with dynamic, high-resolution environmental data. Therefore, it remains a problem to provide an improved method for use in maintenance of sculpted landscapes, as well as needs for devices that overcome one or more of the aforementioned problems.

[0009] Summary

[0010] In a first aspect, a computer-implemented method is disclosed for estimating evapotranspiration of a sculpted landscape, such as a golf course, wherein the sculpted landscape comprises a surface and one or more objects, such as buildings or trees, and the method comprises the steps of:

[0011] a) obtaining a geolocation of the surface of the sculpted landscape

[0012] b) obtaining a digital surface model, DSM, of the sculpted landscape, wherein the DSM comprises an elevation of the surface of the sculpted landscape and dimensions of the objects raising from the surface of the sculpted landscape;

[0013] c) subdividing the surface of the sculpted landscape into a plurality of sub-areas, d) determining, for one or more of sub-areas of the plurality of the sub-areas, a shadow value indicative of an amount of sunlight incident on the respective sub-area over a predetermined time interval by a sun ray tracing model and the geolocation,

[0014] e) obtaining a set of weather data indicative of meteorological conditions for the sculpted landscape,

[0015] f) determining, for the one or more sub-areas of the plurality of sub-areas, an estimated irradiation value by using the set of weather data and the shadow value for said predetermined time interval,

[0016] g) determining, for the one or more sub-areas of the plurality of sub-areas, an estimated evapotranspiration value by using the estimated irradiation value and the set of weather data into an evapotranspiration model, the estimated evapotranspiration value being determined for said predetermined time interval.

[0017] Consequently, the computer-implemented method allows to generate sub-areas in a sculpted landscape that may have a high spatial resolution. Similarly, the method allows to categorize said sub-areas based on the shadow value such as to determine whether irradiation from the Sun reaches the sub-area or has been blocked by a foreign object. Thus, the shadow value provides, together with the set of weather data, an irradiation value that may have a high temporal resolution. Overall, the shadow value and sub-area subdivision allow to accurately determine evapotranspiration values in both shaded and sunlit regions present in any one or more of sub-areas of the plurality of areas. This first aspect of the disclosure provides any sculpted landscape manager, e.g. a greenkeeper, a method to irrigate an area by making informed decisions regarding the evapotranspiration that has occurred in the sculpted landscape. Moreover, it also allows for automated irrigation systems to be set in optimal places of the sculpted landscape. In the method, by relying on the sub-areas and shadow values, an accurate estimation of an evapotranspiration value can be determined, which, in turn, allows for planning and executing an irrigation recommendation on a sculpted landscape, thereby allowing determination of a predictable and precise irrigation output in sculpted landscapes.

[0018] The sculpted landscape may comprise a surface indicative of a natural topography and one or more objects raising from said surface. Alternatively or additionally, the one or more objects may be erected from said surface. Examples of objects raising the ground may be, but not limited to, plant canopies like trees or bushes; elevation topography, e.g. hills, mountains, and / or artificial structures, e.g. obstacles, houses, buildings. In some implementations, the dimensions of said objects may be expressed relative to the surface. In alternative implementations, the dimensions of said objects may be absolute and encompassing the height of an elevation topography.

[0019] The geolocation may be a location, such as a set of coordinates, an area, a climate zone, or the like of the sculpted landscape. In some embodiments, the geolocation may be or comprise a set of location values indicative of a latitude and longitude of the sculpted landscape, such as of a geometrical centre of the sculpted landscape.

[0020] In some implementations of the first aspect in this disclosure, the geolocation may be obtained through any global positioning system (GPS), global navigation satellite system (GNSS), network-based positioning, or sensor fusion techniques.

[0021] By combining DSM elevation data with geolocation, the invention facilitates accurate mapping, navigation, and spatial analysis of the sculpted landscape. The DSM may comprise elevation data representing from plant canopies, elevation topography and artificial structures, within a defined geographic region. By incorporating these features, the DSM provides a comprehensive three-dimensional representation of the surface, enabling accurate height measurements of objects relative to the underlying terrain. The DSM may be generated from remote sensing data, such as LiDAR point clouds or photogrammetric imagery, and processed through interpolation or filtering algorithms to produce a continuous elevation model. DSM may be understood to be equivalently to digital terrain models (DTM), while including above-ground features from the surface by the skilled person. Therefore, digital representations of the sculpted landscape from DSM may be obtained comprising the surface of the sculpted landscape, which is determined by the elevation data, and one or more objects raising from said surface. In some implementations, the DSM may be obtained from a remote database, such as cloud storage server, and in alternative implementations, the DSM may be obtained via generation of DSM-files, e.g. by using a drone comprising a plurality of sensors configured to map the sculpted landscape.

[0022] The step of subdividing the surface into a plurality of sub-areas may further comprise a step subdividing a representation of the surface, such as a map or model of the surface, into a plurality of subareas. Alternatively or additionally, the step of subdividing the surface into a plurality of sub-areas may comprise subdividing the DSM of the surface, i.e. subdividing portions of the DSM of the sculpted landscape corresponding to the surface into the sub-areas.

[0023] Each sub-area may be and / or correspond to a respective portion of the surface and / or DSM, respectively. The sub-areas may be non-overlapping.

[0024] Throughout the present description, the term "value" refers to a parameter, metric, or numerical representation indicative of a physical quantity, condition, or state relevant to the operation or control of a system or method. A value may be expressed in absolute or relative terms and may correspond to a measured, estimated, calculated, or predetermined quantity. In the first aspect of this disclosure, the term "estimated value" may be understood by the skilled person as a value that has been derived, refined, or otherwise improved relative to a value obtainable from another source or by a more basic calculation. The estimated value may incorporate adjustments, corrections, or predictive modelling to enhance accuracy or relevance for a given application. Therefore, an adjusted / modified / corrected estimated value may be referred to in this disclosure as an "estimation". In the first aspect of this disclosure, the computer implemented method allows to determine the shadow value, the estimated irradiation value, and the estimated evapotranspiration value.

[0025] The shadow value may be a value indicative of the amount of sunlight incident on the respective sub-area. Additionally or alternatively, the shadow value may be indicative of a shaded region and a sunlit region. The shadow value may be a discrete binary value. Additionally or alternatively, the shadow value may be a continuum of values indicative of the amount of sunlight incident on the respective sub-area e.g. a vector.

[0026] The shadow value may be obtained by means a solar ray tracing model. The solar ray tracing model may be configured to model or provide at least an amount of incident sunlight on the respective sub-area. In some embodiments, the solar ray tracing model is furthermore configured to model or provide an incident angle of sunlight on the respective sub-area. It will be appreciated that the solar ray tracing model may apply any commonly known ray tracing algorithm.

[0027] An "irradiation value" in this disclosure refers to a value representative of a solar radiation, i.e. an energy received from the sunlight's radiation per unit area at a given moment. The skilled person may understand that, within the context of this disclosure, the terms "solar radiation," "solar irradiation," and "solar exposure" may be used interchangeably, notwithstanding differences in their conventional units of measurement. Such interchangeable use is intended to encompass any representation of solar energy or sunlight received by a surface, whether expressed as instantaneous intensity, cumulative energy over time, or qualitative exposure.

[0028] An "irradiation value" may be a value indicative of a solar radiation and / or a measure of solar radiation, to which the subarea is subjected. In contrast, the "estimated irradiation value" may be a calculated / determined value indicative of a solar radiation of the surface of the respective sub-area over or during a predetermined time interval, such as an estimated accumulated solar radiation of the surface of the respective sub-area over or an estimated solar radiation during a predetermined period of time. For instance, an "average irradiation value" for an entire sculped landscape may obtained from weather parameters. Thereby, the skilled person may be able to obtain an average irradiation value over an entire sculpted landscape from the set of weather parameters. The average irradiation value may be used as a reference. In contrast, the estimated irradiation value may be an irradiation value calculated using the shadow value and the set of weather data for a sub-area.

[0029] The estimated irradiation value may be a predicted irradiation value at the sub-area corresponding to the amount of sunlight incident (solar irradiation) on the respective subarea as determined by the set of weather data and the shadow value. The estimated irradiation value may be compared to the average irradiation value that may be used as a reference.

[0030] The estimated irradiation value may comprise a plurality of estimated irradiation values, e.g. a first and second estimated irradiation values. Each estimated irradiation values may be associated to the same sub-area or a different sub-area of the plurality of sub-areas.

[0031] In an example, the shadow value (SV) may be a binary discrete value. When SV = 0 the shadow value may indicate that Sunlight is blocked in the sub-area. Alternatively or additionally, in the same sub-area or a different sub-area, if SV = 1 the shadow value may be indicative that Sunlight reaches the surface of the sculpted landscape. When SV = 1, the estimated irradiation value at the sub-area may correspond to an amount of sunlight incident on the respective sub-area as determined by the set of weather data, such as from a net solar irradiation extracted from the set of weather data. When the SV = 0, the estimated irradiation value at the sub-area may be zero. Alternatively, when the SV = 0 the estimated irradiation value may comprise a non-zero contribution associated with an irradiation value originating from reflected or diffuse amounts of sunlight in nearby surroundings.

[0032] In a further example, if an "average irradiation value" for an entire sculpted landscape is obtained to be, e.g., of 1000 W / m2, a first estimated irradiation value may be found to be, e.g., 1000 W / m2 in a sunlit sub-area (SV = 1), while a second estimated irradiation value may be found to be, e.g., 0 W / m2 in a shaded sub-area (SV=0). Therefore, the estimated irradiation value comprising a first and second irradiation values may be more precise than the average irradiation value for an entire or large area of the sculpted landscape.

[0033] The estimated irradiation value in a sunlit sub-area may also be adjusted based on the weather data obtained, such as to provide more accurate values in the sunlit sub-area compared to an average irradiation value. In the aforementioned example, when an estimated irradiation value may be an irradiation of e.g. 1000 W / m2 in a sunlit sub-area (SV = 1), an irradiation estimate of 900.5 W / m2 may be found in said sub-area.

[0034] In the calculation of the shadow value of this disclosure, a sun ray tracing model is employed. The sun ray tracing model may be configured to simulate the propagation of solar rays towards a defined sub-area. The sun ray tracing model may determine the position of the Sun relative to the Earth based on a temporal resolution and geolocation parameters, such as date, time, latitude, and longitude, using astronomical algorithms. The sun ray tracing model may comprise information indicative of reflection, absorption, scatter or other light-matter interaction phenomena. For instance, Sun rays in the sun ray tracing model may be configured to be traced to such as to determine illumination / irradiation values and establish shadow patterns on surfaces and objects within the area as indicated by the shadow value. This enables accurate and precise computations of solar exposure as well as shading effects.

[0035] In the first aspect of this disclosure, the evapotranspiration model may comprise any suitable model predictive of at least one evapotranspiration value. The skilled person will understand that, while direct solar irradiation has a strong effect on evapotranspiration, an evapotranspiration value may also be determined even in areas where sunlight is blocked. For instance, due to reflected solar irradiation, or diffuse solar irradiation reaching a shaded area, evapotranspiration may still take place in such shaded areas. Alternatively, evapotranspiration may occur as a result of other parameters in each sub-area, e.g. soil heat flux, mean temperature, atmospheric pressure, water vapor pressure, rates of saturation of the water-vapor pressure, and / or windspeed that may also influence the obtained evapotranspiration value.

[0036] The term "predetermined time interval" in this disclosure may refer to a time interval of data acquisition over a desired time period. Therefore, the time interval of data acquisition is associated with a temporal resolution to estimate evapotranspiration while the desired time period is indicative of a predictive power of said estimation in the computer-implemented method. The evapotranspiration value may be a value for evapotranspiration corresponding to an amount of water removed from the surface of the sculpted landscape. An "average evapotranspiration value" may refer to a value for evapotranspiration of an entire sculpted landscape using any evapotranspiration model. The skilled person may be able to calculate an average evapotranspiration value over an entire sculpted landscape using any evapotranspiration model, or alternatively extract from the set of weather data an average evapotranspiration value. An "average evapotranspiration value" may be used as a referential evapotranspiration. From this disclosure, it is understood that the average evapotranspiration value may differ from the estimated evapotranspiration value obtained in the first aspect of the invention, where the estimated evapotranspiration value may be estimated by using the estimated irradiation value in each sub-area. The estimated evapotranspiration value may be compared to the average evapotranspiration value as a reference.

[0037] For example, an average evapotranspiration value over an entire sculpted landscape may be 5 mm / h. However, in a sunlit sub-area of the sculpted landscape, the estimated evapotranspiration value that may be obtained may be e.g. 6.3 mm / h. In this example, the estimated evapotranspiration may be a more precise value than what is found with an average evapotranspiration value.

[0038] While steps a),b),c),d),e) and f) are described subsequently in the method, it will be appreciated that the steps may be performed in parallel or in a different order. For instance, the step e) of obtaining the weather data may be performed prior to or in parallel with any one of steps a),b),c),d). Alternatively or additionally, the step of obtaining a) the geolocation may be performed in parallel with any one of steps b),c),d).

[0039] It will be appreciated throughout the present disclosure that a digital surface model (DSM) refers to a model indicative of a surface of the sculpted landscape, including at least objects on the surface constructions and at least some vegetation, such as trees, shrubs, etc. For instance, the DSM may be or comprise a surface model including constructions and vegetation having a height of at least 50 cm, such as at least 75 cm, such as at least 1 m. It will moreover be appreciated that such models in themselves are well-known in the art. It will furthermore be appreciated that any existing DSM may be used in the context of the present disclosure.

[0040] Alternatively or additionally, the DSM may be obtained by means of a number of photographic images of the sculpted landscapes, such as a plurality of images obtained via a drone. The images may be stitched together using well-known stitching techniques and a DSM may be determined based on the stitched images of the sculpted landscape.

[0041] The set of weather data may comprise at least a reference solar irradiation value, such as a direct normal irradiance for a portion of the surface of the sculpted landscape. Moreover, the set of weather data may indicate a portion of clear sky covered by clouds that is associated with a reflected irradiance onto the surface of the sculpted landscape. The reference solar irradiation value may be a net solar irradiation arriving at the surface of the sculpted landscape and may be configured to be adjusted after determination of the estimated solar irradiation value.

[0042] In some embodiments, each of the plurality of sub-areas comprise one or more types of turf canopies.

[0043] In some embodiments, the computer-implemented method, further comprises the steps of:

[0044] determining, based on the DSM, a surface normal vector to a surface of the subarea

[0045] determining an irradiation estimation reaching a sub-area of the sculpted landscape, the irradiation estimation being derived from the estimated irradiation value, and wherein the estimated irradiation value comprises a combination of a direct normal irradiance dependent on an angle of incidence of sunlight with respect to said surface normal vector and a diffuse horizontal irradiance indicative of sunlight scattering.

[0046] The irradiation estimation reaching a sub-area may be at least one part of the estimated irradiation value configured to be within a sub-area of the plurality of sub-areas. Alternatively, the irradiation estimation reaching a sub-area may be an entire part of the estimated irradiation value, wherein the estimated irradiation value is configured to be adjusted with the combination of the direct normal irradiance and the diffuse horizontal irradiance. Thereby, the irradiated estimation allows for an adjustment of the irradiation value in a sunlit (non-shaded) area to, in turn, obtain a more accurate and precise irradiation value in a sub-area.

[0047] Consequently, for one or more sub-areas, the estimated irradiation value may be a result from adding the direct normal irradiance (DN I) to the diffuse horizontal irradiance (DHI). In some implementations, the irradiation estimation reaching a sub-area of the sculpted landscape may equivalently be expressed as a global horizontal irradiance (GHI) via the following equation GHI = DNI x cos(0) + DHI, wherein the DNI and the DHI may be obtained from a reference solar irradiation that may be comprised by the set of weather data, and (0) is a Sun's azimuth angle,. Alternatively, the GHI may be directly obtained from the set of weather data.

[0048] By a surface normal vector may herein be understood a vector orthogonal and / or normal to the surface of the respective subarea. The surface normal vector may be orthogonal and / or normal to at least a part of the surface of the respective sub-area and / or may be orthogonal and / or normal to an average or smoothed surface of the respective sub-area.

[0049] The direct normal irradiance may be scattered sunlight measured at the surface of the sculpted landscape. Moreover, the direct normal irradiance may be dependent on a Sun's azimuth angle (θ). Additionally, the diffuse horizontal irradiance may be scattered sunlight from the sky when reaching the surface of the sculped landscape but excluding direct rays from the Sun.

[0050] In some embodiments, the computer-implemented method, wherein prior to step (e) it further comprises the steps of:

[0051] determining, based on the shadow value, a sunlit region and a shaded region in the one or more sub-areas of the plurality of sub-areas,

[0052] wherein the determined estimated irradiation value of step (f) comprises, in each the one or more sub-areas, a first irradiation estimation determined for the sunlit region and a second irradiation estimation determined for the shaded region,

[0053] and wherein the determined estimated evapotranspiration value comprises

[0054] a first evapotranspiration estimation associated with the sunlit region and obtained by using the evapotranspiration model, the first irradiation estimation, and the set of weather data, and

[0055] a second evapotranspiration estimation associated with the shaded region and obtained by using the evapotranspiration model, the second irradiation estimation, and the set of weather data.

[0056] Therefore, a first irradiation estimation in the sunlit region may be established after determining the shadow value in each sub-area, which in turn, allows to clearly divide each sub-area in sunlit and shaded regions. Thereby a more precise evapotranspiration may be obtained, such as with a higher spatial resolution across the area.

[0057] For sub-areas where sunlit and shaded regions may be determined, the estimated irradiation value in a sunlit sub-area may be determined based on the weather data obtained, such as to provide more accurate values in the sunlit sub-area compared to an average irradiation value for an entire surface of the sculpted landscape.

[0058] A sunlit region may be a non-shaded region, or alternatively a remaining area after determination of a shaded region in a sub-area using the shadow value. A shaded region may be an area where sunlight is blocked.

[0059] In some embodiments, the sub-areas may comprise at least one portion of sunlit region, at least one portion of shaded region or a combination thereof. Additionally or alternatively, the sub-areas may span a plurality of sunlit regions and a plurality of shaded regions. In alternative embodiments, the sub-area may comprise a complete sunlit region within said sub-area or a complete shaded region within said sub-area.

[0060] For each such sunlit and shaded regions in each of the sub-areas, an estimated evapotranspiration value may be indicated as determined from the first and second evapotranspiration estimation. Additionally or alternatively, the computer-implemented method may be configured to determine evapotranspiration estimations in sunlit and shaded regions. The determined evapotranspiration estimations may be translated to irrigation needs for each sub-area.

[0061] In an example applied to a sculpted landscape, where the sculpted landscape in subdivided in sub-areas, an average irradiation value of an entire sculpted landscape may be found to be e.g. 1000 W / m2. Here, a sub-area is further divided into sunlit and shade regions, where a first irradiation estimation of e.g. 900.5 W / m2 may be found in the sunlit region, while a second irradiation estimation of e.g. 0 W / m2 may be found in the shaded region. Alternatively, the second irradiation estimation e.g. 5.4 W / m2 may be found of in the shaded region originating e.g. from diffuse light scattering. Consequently, the determined estimated irradiation value comprising the first and second irradiation estimations of the sunlit (900.5 W / m2) and shaded (5.4 W / m2) regions provide a more accurate estimation value in the sub-area than an average irradiation value (1000 W / m2) for an entire surface of the sculpted landscape. Thereby, the determined estimated irradiation value comprising the first and second evapotranspiration estimations provide a more accurate estimation value in the sub-area than an average evapotranspiration value.

[0062] In some embodiments, the computer-implemented method further comprises the steps of: combining, for one or more of sub-areas of the plurality of the sub-areas, the estimated evapotranspiration value into an estimated evapotranspiration map of the sculpted landscape.

[0063] Consequently, the estimated evapotranspiration map provides an overview of a all irrigation needs in an entire sculpted landscape.

[0064] The term "map" is intended to encompass any graphical, digital, or data-structured depiction of a surface, area, or landscape, wherein each region or coordinate is linked to a corresponding value. The skilled person may understand that, within the context of this disclosure, an "estimated evapotranspiration map" refers to a representation of spatial regions associated with one or more numerical or qualitative indicators related to the estimated evapotranspiration value, as determined by the first aspect of this disclosure.

[0065] The evapotranspiration map may be generated by using a graphical user interface. Alternatively, or additionally, the evapotranspiration map may be generated by overlaying the estimated evapotranspiration values for each of the sub-areas of the sculpted landscape onto a digital map.

[0066] In alternative implementations, the evapotranspiration map be generated by stitching data associated with each sub-area to form a map as a graphical user interface. In some embodiments, the computer-implemented method further comprises the steps of:

[0067] h) obtaining, for the one or more sub-areas of the plurality of sub-areas, a sub-area crop coefficient,

[0068] i) determining, for the one or more sub-areas of the plurality of sub-areas, an estimated crop evapotranspiration value by using the estimated evapotranspiration value and the sub-area crop coefficient into a crop evapotranspiration model, the estimated crop evapotranspiration value being determined for said predetermined time period.

[0069] Therefore, having a crop-dependent estimation increases accuracy in estimated evapotranspiration value, particularly when there are different types of turf canopies in each sub-area.

[0070] As used herein, the term "crop coefficient" refers to a dimensionless factor indicative of the relationship between the evapotranspiration of a specific crop under given conditions and an estimated evapotranspiration value for a sub-area. The estimated evapotranspiration value may be a reference evapotranspiration value for said sub-area. The crop coefficient may vary based on crop type, growth stage, canopy characteristics, and environmental factors, and may be expressed as a single value, a range, or a timedependent function.

[0071] In some embodiments, the computer-implemented method as disclosed, wherein the evapotranspiration model is a reference evapotranspiration model, and wherein determining estimated evapotranspiration value comprises the steps of:

[0072] providing the estimated irradiation value and the set of weather data to the reference evapotranspiration model, thereby determining a reference evapotranspiration value ETO.

[0073] For instance, ETO may be calculated using the Peinman-Monteith (PM) model, as outlined by the following equation:

[0074] A ■ (Rn - G) + pacp

[0075] ETO = - - - - 2 ■ ( A + y (1 +

[0076]

[0077] y '1a'

[0078] where ETO is a reference evapotranspiration (e.g. in mm / day), Rnis a net radiation at the crop surface, G is soil heat flux (in e.g. MJ / m2 / day), es- eais the saturation vapor pressure deficit (in e.g. kPa) between saturation vapor pressure (es) and average actual vapor pressure (ea), A is a rate of the vapor pressure curve (in e.g. kPa / °C), y is the psychrometric constant (kPa / °C) that is dependent on atmosphere pressure (p), y = 0.665 - 10-3■ p, = πr-2rsis a surface resistance dependent on crop type and stomatal conductance, rais an aerodynamic resistance dependent on wind speed and canopy height, pais air density, cpis the specific heat of air, and X is the Latent heat of vaporization.

[0079] In some embodiments, the reference evapotranspiration ETO may be approximated by the FAO56-Peinman-Monteith (FAO-56) model, as obtained by the following equation:

[0080] 37

[0081] >_ 0.408A ■ (Rn - G) + yr +%73u2(es(Th) - ea(T, RH)

[0082] E

[0083]

[0084] T® A + y(l + 0.34U2) Thereby, simplifications to the PM model are made such as: (1) Fixed resistances assuming reference grass crop with constant surface resistance of rs=70s / m, raderived from standard wind speed at 2 m and U2 being an average hourly wind speed measured at height 2 m. Moreover, (2) simplified constants are introduced converting physical terms into empirical coefficients (e.g. "37" is a factor for wind term) and T indicates a mean daily air temperature; and (3) units for ETO are expressed in the FAO-56 model as mm / day for ETo. Additionally, in some implementations using the FAO-56 model, the actual vapor pressure of the FAO-56 model may be determined as a function of temperature (T) and relative humidity (RH ),

[0085] ( / ? / / \

[0086]

[0087] 100 /

[0088] and wherein the saturation vapor pressure may be calculated as,

[0089] es(T) = 0.6108exp(17.27T / \

[0090] es(T) = 0.6108exp ■ ( )■

[0091]

[0092] \ 1 i I kJ liJ /

[0093] In some implementations using the FAO-56 model, the saturation vapor pressure, es,

[0094] (172 'JTT \

[0095]

[0096] — T^ +:— 273 “.3 / )■ In some implementations using the FAO-56 model, an expression for a rate of vapor pressure curve, A, may be obtained from an approximated slope saturation in the vapor pressure curve, such as

[0097] 0.6108exp ■ (

[0098] \T1 h Y I 97 / 0 did q / ) J

[0099] A = - - -

[0100]

[0101] (T + 273.3)2

[0102] In some implementations, parameters of the PM model may differ between daytime and nighttime.

[0103] In a preferred embodiment, for time intervals comprising an hourly calculation, soil heat flux (G) may be approximated during daylight and nighttime as a fraction of net irradiation Rn. For example, G(t h)=0.1Rn, where G (t h)=0.5Rn.

[0104] In some implementations using the FAO-56 model, an approximation for wind speed

[0105] at 2 m height (u2) be provided as, u2= uz4.87 / ln(67.8z+5.42) wherein z is a height measurement above ground surface.

[0106] In some implementations using the FAO-56 model, the net radiation at the crop surface Rnmay be calculated as a difference between incoming net short wave irradiation, Rns, and outgoing net long wave irradiation, Rni, such that Rn= Rns- Rni,

[0107] In some implementations of the FAO-56 model, the incoming net short wave irradiation is a fraction of the solar irradiation that is not reflected from the surface, such that Rn=(l-a) Rs, and wherein a is an albedo or a canopy reflection or a value indicative of an albedo or a canopy reflection.. In some implementations of the FAO-56 model, the net long wave irradiation may be approximated as,

[0108] Rnl= o-T4(0.34 - 0.14A / e^) (1.35^ - 0.35), wherein a = 2.043 ■ IO"10, which is

[0109]

[0110] Stefan-Boltzman constant in MJ ■ rrr2■ h1, and Rso is a clear sky radiation. Additionally, the temperature T may be an hourly temperature Th.

[0111] In some implementations of the FAO-56 model, net radiation at the crop surface Rsmay be derived from a direct normal irradiance (DNI). Alternatively, Rsmay be the direct normal irradiance (DNI).

[0112] In some embodiments, the computer-implemented method as previously disclosed, wherein determining the estimated crop evapotranspiration value comprises the steps of:

[0113] providing the reference evapotranspiration ETO and the sub-area crop coefficient to the crop evapotranspiration model, thereby determining a crop evapotranspiration value ETc by ETc=Kc·ET0.

[0114] Consequently, since crop coefficient may vary based on crop type, growth stage, canopy characteristics, and environmental factors, it may be beneficial due to higher accuracy and precision to calculate crop evapotranspiration values for each sub-area.

[0115] In some implementations, the crop coefficient may be a basal crop coefficient (Kc=Kcb) or a dual crop coefficient taking into account also soil-water evaporation Ke, i.e. Kc= Kcb + Ke.

[0116] In some embodiments, the computer-implemented method further comprising the step of:

[0117] updating dynamically, upon a predetermined time interval, the estimated evapotranspiration value for the one or more sub-areas of the plurality of sub-areas.

[0118] By updating dynamically is herein to understand a repetitive action to provide updated estimated evapotranspiration values with present data available at a given time.

[0119] The predetermined time interval may be at least 1 second, such as between 1 second and 24 hours, such as between 30 seconds and 12 hours, such as between 1 minute and 6 hours, such as between 15 minutes and 4 hours.

[0120] In some embodiments, the computer-implemented method herein disclosed, wherein the predetermined time interval, from step d) in the first aspect, comprises an acquisition data period and a predictive time period, the acquisition data period selected from a range between a 15 minutes up to an hour and the predictive time period selected from a range between one day up to 14 days.

[0121] Consequently, the acquisition data period may provide a high temporal resolution to the resulting estimated evapotranspiration value, while the predictive time period may provide a high predictive power in the estimated evapotranspiration value.

[0122] In some embodiments, the computer-implemented method herein disclosed, wherein each sub-area comprises a predetermined mesh element configured to be the equal across all plurality of sub-areas, and wherein a size of the mesh element for each of the plurality of areas is between 0.05 m2and 20 m2, and preferably between 5 to 10 m2.

[0123] In some implementations of this embodiment, the mesh element may be square shaped. In alternative implementations the mesh element may be triangular shaped.

[0124] The mesh element may allow to form a coherent and uniform mesh grid covering each of the plurality of sub-areas.

[0125] The size of the mesh element and the sizes of the sub-areas may determine the spatial resolution of the estimated evapotranspiration value as a trade-off with respect to computational time. For instance, the smaller the size of the mesh element the higher the spatial resolution, however, the longer the computational time. For golf courses, it may be beneficial to use a size of the mesh element between 5 to 10 m2.

[0126] In some embodiments, the computer-implemented method further comprises the steps of:

[0127] receiving input from a user indicating an alteration in the dimensions of any one or more objects raising from the surface of the sculpted landscape,

[0128] modifying the DSM of the sculpted landscape into an altered DSM based on said input from the user,

[0129] repeating at least steps d), f) and g) based on the altered DSM.

[0130] Therefore, the estimated irradiation value and consequently the estimated evapotranspiration value may differ upon alteration of dimensions of any one or more objects raising from the surface of the sculpted landscape. Correspondingly, a consequence of a potential alteration to the evapotranspiration of at least some sub-areas of the sculpted landscape may be simulated.

[0131] An altered DSM may result from removal or trimming of, e.g., a tree. In an example, in which a tree or other vegetation is removed, the shadow cast on one or more sub-areas may be reassessed, which, in turn, may lead to an increase in the estimated irradiation value and similarly to an increase in the estimated evapotranspiration value.

[0132] In some embodiments, the computer-implemented method further comprises the steps of:

[0133] obtaining an updated digital surface model, DSM, of the sculpted landscape, wherein the DSM comprises an alteration in the dimensions of any one or more objects raising from the surface of the sculpted landscape;

[0134] replacing the DSM of the sculpted landscape by the updated DSM,

[0135] repeating at least steps d), f) and g) based on the altered DSM. Therefore, the estimated irradiation value and consequently the estimated evapotranspiration value may differ upon replacing a first DSM by the updated DSM comprising the alteration.

[0136] An updated DSM may result from a change in a dimension of an object raising from the surface (e.g. a tree growing). Additionally or alternatively, an updated DSM may result from a weather event that results in a modified sculpted landscape (e.g. a tree removed due to strong winds), thereby rendering a different DSM from the original obtained DSM. This leads to an updated estimated irradiation value and similarly to an updated estimated evapotranspiration value.

[0137] In some embodiments, the computer-implemented method further comprises the step of:

[0138] generating, for the one or more sub-areas of the plurality of sub-areas, a predictive evapotranspiration estimation model indicative of future irrigation needs for the sculpted landscape.

[0139] Thereby, a user performing the computer implemented method may obtain a fast and efficient answer regarding an amount of water required for a particular sub-area or an entire sculpted landscape.

[0140] A future irrigation need may be associated with an amount of water to be provided to grass or canopies present in a sub-area.

[0141] A predictive evapotranspiration estimation model may refer to a computational, mathematical, or algorithmic representation configured to simulate, predict, or estimate a an evapotranspiration value based on one or more input parameters.

[0142] The predictive evapotranspiration estimation model may include, but is not limited to, deterministic or probabilistic components and may utilize empirical data, theoretical relationships, or machine learning techniques to generate outputs. The outputs of the model may include predictions, risk assessments, or recommended actions, and the model may be adapted to update dynamically based on new data or changing conditions.

[0143] In some embodiments, the computer-implemented method herein disclosed, wherein the predictive evapotranspiration estimation model is generated by:

[0144] processing the set of weather data using a machine learning data architecture, the machine learning data architecture being applied the evapotranspiration model, and wherein the machine learning data architecture is trained to determine an estimated evapotranspiration value based on one or more of the selected list: a baseline evapotranspiration history, a determined estimated evapotranspiration history, historical weather data, forecast weather data, an irrigation input history, and soil moisture data. The machine learning (ML) data architecture may belong to a pre-existing or newly created ML architecture, e.g. the ML model may be based on neural networks, support vector machines, and / or genetic algorithms among other models comprising artificial intelligence.

[0145] The machine-learning data architecture may be trained based on a training data set comprising, e.g., an estimated evapotranspiration value from ten sculpted landscapes located in ten different geolocations, in each respective geolocation, 200 days of historical weather conditions, and 200 estimated evapotranspiration values for each of the sub-areas of the plurality of sub-areas in each of the sculpted landscapes. The estimated evapotranspiration value in the training data set may be obtained manually based on observations from computer registrations and may be provide an indication of future irrigation needs in each said sub-area. Additionally or alternatively, the observations and parts of the information in the training data set may also be made provided by a turf manager in the sculpted landscape e.g., a groundskeeper or a greenkeeper.

[0146] In some embodiments, the computer-implemented method, further comprises the steps of:

[0147] determine, for one or more sub-areas of the plurality of sub-areas, a surface temperature value based on a leaf temperature model, wherein the leaf temperature model is configured to receive the set of weather data and the estimated irradiation value in the one or more sub-areas.

[0148] Consequently, besides the estimated evapotranspiration value for the sculpted landscape, an estimated surface temperature value may be provided. This may be useful for decision making in irrigation and turf management. For example, a correlation guide between amount of evapotranspiration and an accurate surface temperature may be established, in order to decide to set up a shade on areas with extreme surface temperatures.

[0149] As used herein, a "leaf temperature model" refers to a computational or mathematical representation configured to estimate or predict the temperature of a plant leaf based on one or more input parameters. Such parameters may include, without limitation, ambient air temperature, solar radiation, wind speed, relative humidity, and transpiration rate. The model may incorporate energy balance principles, accounting for heat gain from solar exposure and heat loss through convection, radiation, and evapotranspiration. The output of the model may be expressed as an absolute temperature value or as a relative deviation from ambient temperature, and may be utilized for other applications such as physiological analysis, stress prediction, or disease risk assessment.

[0150] In some implementations, each sub-area comprising a different canopy or grass may be approximated as a plurality of leaves.

[0151] Therefore, this allows to simplify the mathematical calculations associated with determination of an estimated surface temperature.

[0152] In some implementations, the estimated surface temperature value may be a parameter indicative of the thermal condition of a surface of the sculpted landscape. The estimated surface temperature value may be a temperature determined or estimated at a surface defining a soil-air interface in the sculpted landscape.

[0153] In some embodiments, the computer-implemented method further comprises the steps of: determining, for one or more sub-areas of the plurality of sub-areas, a surface soil temperature value based on a soil temperature model, wherein the soil leaf temperature model is configured to receive the estimated irradiation value in the one or more sub-areas.

[0154] Consequently, besides the estimated evapotranspiration value for the sculpted landscape, an estimated soil temperature value may be provided. This may be useful for decision making in irrigation and turf management. For example, soil in certain sub-areas may be too dry, and may need to be replenished by a new fresh soil.

[0155] As used herein, a "soil temperature model" refers to a computational or mathematical representation configured to estimate, predict, or simulate the temperature of soil at one or more depths based on environmental and physical parameters. Such parameters may include, without limitation, ambient air temperature, solar radiation, soil moisture content, thermal conductivity, wind speed, and surface conditions. The model may incorporate heat transfer principles, including conduction, convection, and radiation, and may account for diurnal and seasonal variations. The output of the soil temperature model may be expressed as an absolute temperature value, a temperature profile across multiple depths, or a deviation from a reference temperature, and may be utilized for other applications such as plant growth modelling, irrigation scheduling, and disease risk assessment.

[0156] In some implementations, the estimated soil temperature value may be a parameter indicative of the thermal condition of the uppermost soil layer. This is typically a temperature determined or estimated at or near the soil-air interface. The estimated soil temperature value may represent an instantaneous temperature reading, an averaged temperature over a defined time interval, or a predicted temperature derived from environmental inputs such as solar radiation, air temperature, soil moisture, and wind speed.

[0157] In some embodiments, the computer-implemented method further comprises the steps of: determining, for the one or more sub-areas of the plurality of sub-areas, a probability for pathogenic infection presence in the surface of the sculped landscape by using a turf predictive disease model, wherein the turf predictive disease model is configured to receive the set of weather data, the estimated irradiation value, and the surface temperature value in the one or more sub-areas.

[0158] Consequently, besides the estimated evapotranspiration value for the sculpted landscape, an estimated probability for pathogenic infection may be found. This may be useful for decision making in irrigation management. For example, certain sub-areas may be damaged by a disease, which may decrease roll balling performance in a sub-area of the surface of the sculpted landscape. Infected sub-areas may therefore require a different water irrigation amount.

[0159] By "a probability for pathogenic infection presence" is herein to be understood an indication of a disease pressure in the surface of the sculped landscape. Disease pressure in this disclosure may be understood by the skilled person as a combined influence of environmental conditions, pathogen presence, and host susceptibility that determines the likelihood and severity of disease outbreaks. The probability for pathogenic infection presence may be an estimated value e.g. an estimated probability of disease pressure value.

[0160] In some embodiments, the term for "probability for pathogenic infection presence" may be interchangeable with "an estimated probability of disease pressure value".

[0161] In some embodiments, the estimated probability of disease pressure value is indicative of a risk of disease from growth of the surface, such as on grass and an amount of the area of the sculpted landscape, such as a subset of sub-areas.

[0162] The probability for pathogenic infection presence may be calculated using a predictive turf disease model.

[0163] In some embodiments, the "predictive turf disease model" may be interchangeable with "a probabilistic disease pressure model", such as the Smith-Kerns dollar spot model.

[0164] In some embodiments, the computer-implemented method as previously disclosed, wherein the set of weather parameters indicative of meteorological conditions for the sculpted landscape comprise:

[0165] an averaged air temperature,

[0166] an averaged relative humidity,

[0167] a measured averaged wind speed above a predetermined height over the surface sculpted landscape,

[0168] a measured fraction of the sky covered with clouds

[0169] diffuse horizontal irradiance

[0170] direct beam irradiance

[0171] global horizontal irradiance.

[0172] In some embodiments, the set of weather data may further comprise estimated weather data such as an estimated averaged relative humidity, an estimated averaged air temperature.

[0173] In some embodiments, the computer-implemented method as previously disclosed, further comprising the steps of:

[0174] determining, for one or more sub-areas of the plurality of sub-areas, an estimated irrigation value required in said sub-area of the surface of the sculpted landscape based on the estimated evapotranspiration value.

[0175] Consequently, an estimated irrigation value may be used as a recommendation for irrigation of water to a sculpted landscape manager or by an irrigation system. The estimated irrigation value may alternatively or additionally be indicative of a desired or predicted irrigation in said sub-area of the surface of the sculpted landscape.

[0176] The irrigation value in this disclosure refers to a parameter indicative of an estimated irrigation amount, such as an irrigation quantity desired and / or required to achieve or maintain a reference moisture level and / or reference humidity level. The "estimated irrigation value" may be determined based on one or more target conditions and the computer-implemented method herein disclosed and configured to provide an estimated evapotranspiration. The estimated irrigation value may be used to control or adjust irrigation operations accordingly. The estimated irrigation value may be expressed in units similar or identical to those of an estimated evapotranspiration value, for example to indicate a flow rate of water replacement in the sculpted landscape. Alternatively or additionally, the irrigation value may be represented as a volume or as a volume per unit area of the sculpted landscape.

[0177] In some embodiments, the computer-implemented method as previously disclosed, further comprising the steps of:

[0178] receiving, for one or more sub-areas of the plurality of sub-areas, a predetermined threshold evapotranspiration value from a user,

[0179] comparing, for one or more sub-areas of the plurality of sub-areas, the estimated evapotranspiration value to the predetermined threshold evapotranspiration value, determining by said comparison, for the one or more sub-areas of the plurality of sub-areas, a target irrigation value indicative of an estimated irrigation value.

[0180] Therefore, a target irrigation value different to the estimated irrigation value may be employed in order to irrigate the sub-area of the sculpted landscape. This may be particularly helpful in dry regions where restrictions are placed in the amount of water that can be irrigated for the sculpted landscape, or if there is a limited amount of water reserves allocated for the sculpted landscape.

[0181] As used herein, the term "target irrigation value" refers to a predetermined quantitative parameter indicative of a desired water application threshold for an irrigation cycle. Additionally, or alternatively, the term "threshold evapotranspiration value" refers to a predetermined quantitative parameter indicative of a critical level of water loss from soil and vegetation due to combined evaporation and plant transpiration. In some embodiments, the computer-implemented method as previously disclosed further comprising the steps of:

[0182] controlling an irrigation system configured to apply water corresponding to the estimated irrigation value for any one or more sub-areas of the plurality of sub-areas of the surface of the sculpted landscape.

[0183] The irrigation system may comprise an irrigation device, such as fluid supply conduit operatively connected to a pressurized water source and a plurality of discharge elements arranged along the conduit. Each discharge element may include a flow-regulating mechanism adapted to maintain a substantially uniform output regardless of variations in upstream pressure. The irrigation system me be programmed to follow instructions from the computer implemented method herein disclosed.

[0184] A first alternative aspect of this disclosure relates to a computer-implemented method for estimating a surface temperature of a sculpted landscape, such as a golf course, wherein the sculpted landscape comprises a surface and one or more objects, such as buildings or trees, and the method comprises the steps of:

[0185] a) obtaining a geolocation of the surface of the sculpted landscape

[0186] b) obtaining a digital surface model, DSM, of the sculpted landscape, wherein the DSM comprises an elevation of the surface of the sculpted landscape and dimensions of the objects raising from the surface of the sculpted landscape;

[0187] c) subdividing the surface of the sculpted landscape into a plurality of sub-areas, d) determining, for one or more of sub-areas of the plurality of the sub-areas, a shadow value indicative of an amount of sunlight incident on the respective sub-area over a predetermined time interval by a sun ray tracing model and the geolocation,

[0188] e) obtaining a set of weather data indicative of meteorological conditions for the sculpted landscape,

[0189] f) determining, for the one or more sub-areas of the plurality of sub-areas, an estimated irradiation value by using the set of weather data and the shadow value for said predetermined time interval,

[0190] g) determining, for the one or more sub-areas of the plurality of sub-areas, an estimated surface temperature value by using the estimated irradiation value and the set of weather data into a leaf surface temperature model, the estimated surface temperature value being determined for said predetermined time interval. The steps a)-f) in this first alternative aspect may be similar or identical to that of the first aspect disclosed of the present invention. Correspondingly, any feature and embodiments described with respect to steps a)-f) of the method according to the first aspect may equally apply to method steps a)-f) of the method in this first alternative aspect.

[0191] Consequently, the computer-implemented method of this first alternative aspect allows to obtain an estimated surface temperature value for each sub-area that may have a high spatial and temporal resolution. Similarly, the method allows to categorize said subareas based on the temperature value such as to determine where it may be warmest and coldest in the sculpted landscape. This may be useful for turf management forecast.

[0192] In particular, the geolocation, the DSM, the subdivision of the sculpted landscape, the shadow values, the weather data, and / or the estimated irradiation value in the method according to the first alternative aspect may be and / or comprise any feature described with respect thereto with respect to the method according to the first aspect.

[0193] The weather data may be weather data as described with respect to the method according to the first aspect. The size of the sub-areas may be size of the sub-area as described with respect to the method according to the first aspect. The predetermined time interval may be the predetermined time interval as described with respect to the method according to the first aspect. The embodiments of the steps of obtaining and modifying the DSM may be described as embodiments of steps of obtaining and modifying the DSM according to the first aspect.

[0194] The computer implemented method of the first alternative aspect may further comprise the steps of: determining, based on the DSM, a surface normal vector to a surface of the sub-area; and determining an irradiation estimation reaching a sub-area of the sculpted landscape, the irradiation estimation being derived from the estimated irradiation value, wherein the estimated irradiation value comprises a combination of a direct normal irradiance dependent on an angle of incidence of sunlight with respect to said surface normal vector and a diffuse horizontal irradiance indicative of sunlight scattering.

[0195] The irradiation estimation reaching a sub-area may be at least one part of the estimated irradiation value configured to be within a sub-area of the plurality of sub-areas. Alternatively, the irradiation estimation reaching a sub-area may be an entire part of the estimated irradiation value, wherein the estimated irradiation value is configured to be adjusted with the combination of the direct normal irradiance and the diffuse horizontal irradiance. Thereby, the irradiated estimation allows for an adjustment of the irradiation value in a sunlit (non-shaded) area to, in turn, obtain a more accurate and precise irradiation value in a sub-area.

[0196] Consequently, for one or more sub-areas, the estimated irradiation value may be a result from adding the direct normal irradiance (DN I) to the diffuse horizontal irradiance (DHI). In some implementations, the irradiation estimation reaching a sub-area of the sculpted landscape may equivalently be expressed as a global horizontal irradiance (GHI) via the following equation GHI = DNI × cos(θ) + DHI, wherein the DNI and the DHI may be obtained from a reference solar irradiation that may be comprised by the set of weather data, and (θ) is a Sun's zenith angle. Alternatively, the GHI may be directly obtained from the set of weather data.

[0197] By a surface normal vector may herein be understood a vector orthogonal and / or normal to the surface of the respective subarea. The surface normal vector may be orthogonal and / or normal to at least a part of the surface of the respective sub-area and / or may be orthogonal and / or normal to an average or smoothed surface of the respective sub-area.

[0198] The direct normal irradiance may be scattered sunlight measured at the surface of the sculpted landscape. Moreover, the direct normal irradiance may be dependent on a Sun's azimuth angle (θ). Additionally, the diffuse horizontal irradiance may be scattered sunlight from the sky when reaching the surface of the sculped landscape but excluding direct rays from the Sun.

[0199] In some embodiments, of the computer-implemented method of the first alternative method, wherein prior to step (e), the computer-implemented method of the first alternative method further comprises the steps of:

[0200] determining, based on the shadow value, a sunlit region and a shaded region in the one or more sub-areas of the plurality of sub-areas, wherein the determined estimated irradiation value of step (f) comprises, in each the one or more sub-areas, a first irradiation estimation determined for the sunlit region and a second irradiation estimation determined for the shaded region,

[0201] and wherein the determined estimated surface temperature value comprises a first surface temperature estimation associated with the sunlit region and obtained by using the evapotranspiration model, the first irradiation estimation, and the set of weather data, and

[0202] a second surface temperature estimation associated with the shaded region and obtained by using the leaf surface temperature model, the second irradiation estimation, and the set of weather data.

[0203] Therefore, a surface temperature estimation in the sunlit region may be established after determining the shadow value in each sub-area, which in turn, allows to clearly divide each sub-area in sunlit and shaded regions. Similarly, the second surface temperature estimation may be established for a shaded region. Thereby a more precise surface temperature may be obtained, such as with a higher spatial and temporal resolution.

[0204] For sub-areas where sunlit and shaded regions may be determined, the estimated irradiation value in a sunlit sub-area may be determined based on the weather data obtained, such as to provide more accurate values in the sunlit sub-area compared to an average irradiation value for an entire surface of the sculpted landscape.

[0205] A sunlit region may be a non-shaded region, or alternatively a remaining area after determination of a shaded region in a sub-area using the shadow value. A shaded region may be an area where sunlight is blocked.

[0206] In some embodiments, the sub-areas may comprise at least one portion of sunlit region, at least one portion of shaded region or a combination thereof. Additionally or alternatively, the sub-areas may span a plurality of sunlit regions and a plurality of shaded regions. In alternative embodiments, the sub-area may comprise a complete sunlit region within said sub-area or a complete shaded region within said sub-area.

[0207] For each such sunlit and shaded regions in each of the sub-areas, an estimated surface temperature value may be indicated as determined from the first and second surface temperature estimation. Additionally, or alternatively, the computer-implemented method may be configured to determine surface temperature estimations in sunlit and shaded regions.

[0208] In some embodiments, the leaf surface temperature model may be a reference leaf surface temperature model derived from an energy balance equation. In an alternative or additional embodiment, the leaf surface temperature model may disregard heat storage and metabolic heat production. Consequently, a conventional energy balance equation that is easily derivable may be used to provide an estimated surface temperature value.

[0209] In some embodiments, the energy balance equation may comprise an absorbed irradiation being equal to a sum of thermal emission radiation, a sensible heat loss or dry heat transfer due to convention and a latent heat loss due to evapotranspiration.

[0210] In some embodiments, the energy balance equation in the reference leaf surface temperature model may be,

[0211] Rabs- εSσTL4- cpgHa(TL- Ta) - λgvcp= 0,

[0212]

[0213] Pa

[0214] wherein Rabsis an absorbed short and long-wave radiation, ESis an emissivity of surface of the sculpted landscape, a is Stefan-Boltzmann constant, TLis the leaf temperature, cp is a specific heat of air at constant pressure, gHais a boundary layer conductance for heat transfer, Ta is air temperature, A is the latent heat of vaporization of water, gvis vapour conductance, es(TL) is saturation vapour pressure at leaf surface, ea(T^ is vapor pressure of air [kPa], pa - atmospheric pressure.

[0215] In some embodiments, Rabsmay be the estimated irradiation value. Alternatively, in some embodiments, Rabsmay depend on an interaction between radiation and a leaf of interest and view factors for a leaf.

[0216] In a further alternative or additional embodiment, the Rabsmay comprise an absorption of short-wave radiation and absorption of long-wave radiation,

[0217] In some embodiments, the absorption of short-wave radiation may comprise a plurality of first view factors indicative of a direct irradiance, a diffuse irradiance and a reflected irradiance. In some embodiments, the reflected irradiance may be approximated as function of a total short wave irradiance on a surface of the sculpted landscape. In a further embodiment, a view indicative of a direct irradiance may be dependent on a Sun's zenith angle.

[0218] This allows to account for the position of the Sun and its influence on temperature when the Sun's radiation reaches a side of a leaf or a turf canopy in a sub-area.

[0219] In some embodiments, the absorption of long-wave radiation may comprise a plurality of second view factors indicative of an atmospheric thermal radiation and a ground thermal radiation. The atmospheric thermal radiation may be a dependent a fraction of clouds covering a clean sky. In some embodiments, Rabsmay be adjusted from a value for absorbed irradiation in a leaf calculation to a value for absorbed irradiation in a grass calculation.

[0220] This allows for a precise estimation of the absorbed radiation in the sub-area. In some embodiments, the leaf surface temperature model may further comprise a step of obtaining leaf emissivity's and albedo values.

[0221] In some embodiments, the boundary layer conductance for heat may be dependent on windspeed, u, and a characteristic dimension, d, for a leaf, where d may be approximated as d = 0.72w, wherein w is the maximum leaf width in a direction of wind flow

[0222] In some embodiments, the width, d, may be a maximum width in the direction of wind flow.

[0223] This allows for simplification in the mathematical expressions for vapor conductance. In some embodiments, the vapor conductance gvmay be calculated assuming similar or same abaxial and adaxial stomatal conductance.

[0224] This allows for simplification in the mathematical expressions for vapor conductance. In some embodiments, the boundary layer conductance for heat transfer may be calculated as,

[0225] gHa= 1.4 · 0.147 · √(u / d)

[0226] In some embodiments, the saturation vapor pressure may be similar or identical to that of the first aspect of the invention, such that,

[0227] es(T) = 0.6108exp(17.27T /

[0228] es(T) = 0.6108exp ■ (

[0229]

[0230] \ 1 I kJ nJ

[0231] In some embodiments, the leaf surface temperature model may further comprise a step obtaining stomatal conductance for turf grass species.

[0232] Thereby, the leaf surface temperature model may provide a more accurate estimated surface temperature value.

[0233] In some embodiments, the computer-implemented method of the first alternative aspect may further comprise the steps of: combining, for one or more of sub-areas of the plurality of the sub-areas, the estimated surface temperature value into an estimated surface temperature map of the sculpted landscape.

[0234] Consequently, the estimated surface temperature map provides an overview of a temperature distribution for the surface of an entire sculpted landscape.

[0235] The term "map" is intended to encompass any graphical, digital, or data-structured depiction of a surface, area, or landscape, wherein each region or coordinate is linked to a corresponding value. The skilled person may understand that, within the context of this disclosure, an "estimated surface temperature map" refers to a representation of spatial regions associated with one or more numerical or qualitative indicators related to the estimated surface temperature value, as determined by the first alternative aspect of this disclosure.

[0236] In some embodiments, the computer-implemented method of the first alternative aspect further comprising the step of:

[0237] generating, for the one or more sub-areas of the plurality of sub-areas, a predictive surface temperature estimation model indicative of a future surface temperature estimation for the sculpted landscape.

[0238] Thereby, a user performing the computer implemented method of the first alternative aspect may obtain a fast and efficient answer regarding a surface temperature for a particular sub-area or an entire sculpted landscape on a predetermined future date.

[0239] A future surface temperature estimation may be associated with an evapotranspiration value in a sub-area.

[0240] A surface temperature estimation model may refer to a computational, mathematical, or algorithmic representation configured to simulate, predict, or estimate a surface temperature value based on one or more input parameters.

[0241] The surface temperature estimation model may include, but is not limited to, deterministic or probabilistic components and may utilize empirical data, theoretical relationships, or machine learning techniques to generate outputs. The outputs of the model may include predictions, risk assessments, or recommended actions, and the model may be adapted to update dynamically based on new data or changing conditions.

[0242] In some embodiments the predictive surface temperature estimation model may be generated by: processing the set of weather data using a machine learning data architecture, the machine learning data architecture being applied the surface temperature estimation model, and wherein the machine learning data architecture is trained to determine an estimated surface temperature value based on one or more of the selected list: a baseline surface temperature value history, a determined estimated surface temperature value history, historical weather data, forecast weather data, an irrigation input history, and soil moisture data. The machine learning (ML) data architecture may belong to a pre-existing or newly created ML architecture, e.g. the ML model may be based on neural networks, support vector machines, and / or genetic algorithms among other models comprising artificial intelligence.

[0243] The machine-learning data architecture may be trained based on a training data set comprising, e.g., an estimated surface temperature value from ten sculpted landscapes located in ten different geolocations, in each respective geolocation, 200 days of historical weather conditions, and 200 estimated surface temperature values for each of the subareas of the plurality of sub-areas in each of the sculpted landscapes. The estimated surface temperature value in the training data may be obtained from an output of the computer-implemented method herein disclosed. Additionally or alternatively, the estimated surface temperature value in the training data set may be obtained manually based on observations from computer registrations or empirical measurements and may provide an indication of future surface temperature estimations in each said sub-area. Additionally or alternatively, the observations and parts of the information in the training data set may also be made provided by a turf manager in the sculpted landscape e.g., a groundskeeper or a greenkeeper.

[0244] A second alternative aspect of this disclosure discloses a computer-implemented method for estimating a soil temperature of a sculpted landscape, such as a golf course, wherein the sculpted landscape comprises a surface and one or more objects, such as buildings or trees, and the method comprises the steps of:

[0245] a) obtaining a geolocation of the surface of the sculpted landscape

[0246] b) obtaining a digital surface model, DSM, of the sculpted landscape, wherein the DSM comprises an elevation of the surface of the sculpted landscape and dimensions of the objects raising from the surface of the sculpted landscape;

[0247] c) subdividing the surface of the sculpted landscape into a plurality of sub-areas, d) determining, for one or more of sub-areas of the plurality of the sub-areas, a shadow value indicative of an amount of sunlight incident on the respective sub-area over a predetermined time interval by a sun ray tracing model and the geolocation,

[0248] e) obtaining a set of weather data indicative of meteorological conditions for the sculpted landscape,

[0249] f) determining, for the one or more sub-areas of the plurality of sub-areas, an estimated irradiation value by using the set of weather data and the shadow value for said predetermined time interval,

[0250] g) determining, for the one or more sub-areas of the plurality of sub-areas, an estimated soil temperature value by using the estimated irradiation value and the set of weather data into a soil temperature model, the estimated soil temperature value being determined for said predetermined time interval.

[0251] Consequently, the computer-implemented method of this second alternative aspect allows to obtain estimated soil temperature value that may have a high spatial and temporal resolution for each sub-area. The estimated soil temperature value may be used in other predictive models for sculpted landscapes and turf management. This may be useful for turf management forecast.

[0252] The steps a)-f) in this second alternative aspect may be similar or identical to that of the first aspect disclosed in the present invention. Correspondingly, any feature and embodiments described with respect to steps a)-f) of the method according to the first aspect may equally apply method steps a)-f) of the method in this second alternative aspect.

[0253] Moreover, the step g) may be similar or identical to that of the first alternative aspect disclosed in the present invention provided that the leaf temperature model is replaced by a soil temperature model comprising parameters indicative of soil present on the surface of the sculpted landscape. Correspondingly, any feature and embodiments described with respect to step g) of the method according to the first alternative aspect may equally apply method step g) of the method in this second alternative aspect, provided that the leaf temperature model is replaced by a soil temperature model comprising parameters indicative of soil present on the surface of the sculpted landscape.

[0254] The soil temperature model may be configured to determine the soil temperature at a predetermined soil depth from the surface or within a predetermined depth range. In some embodiments, the soil temperature model is configured to determine the soil temperature at a plurality of depths or depth ranges. For instance, the soil temperature model may be configured to determine the soil temperature for a plurality of depths. In one example, the soil temperature model is configured to determine a soil temperature in a depth range of 0.5 - 50 cm, such as 1 - 30 cm, such as 1 - 20 cm below the surface. In this and other examples, the soil temperature model may be configured to determine the temperature, such as a mean temperature, in predetermined intervals, such as predetermined intervals in the depth range. Such predetermined intervals may be, for instance, 0.5 cm, 1 cm, 2 cm, or the like.

[0255] The weather data may be weather data as described with respect to the method according to the first aspect. The size of the sub-areas may be size of the sub-area as described with respect to the method according to the first aspect. The predetermined time interval may be the predetermined time interval as described with respect to the method according to the first aspect. The embodiments of the steps of obtaining and modifying the DSM may be described as embodiments of steps of obtaining and modifying the DSM according to the first aspect.

[0256] By "soil temperature value" this disclosure refers to a value for a thermal property of the soil indicative of the heat energy present at a specified depth and time. In a preferred embodiment, the estimated soil temperature value is a temperature of the soil for each sub-area. Additionally or alternatively, the estimated soil temperature value may be a parameter indicative of the thermal condition of an uppermost soil layer. This is typically a temperature determined or estimated at or near the soil-air interface. The estimated soil temperature value may represent an instantaneous temperature reading, a determined averaged temperature over a defined time interval, or a predicted temperature derived from environmental inputs such as solar radiation, air temperature, soil moisture, and wind speed.

[0257] Consequently, the estimated soil temperature may vary within a sub-area depending on the shadow value or plurality of shadow values determined for said sub-area.

[0258] It will be appreciated that any well-known soil temperature model may be applied. The skilled person may understand that the estimated soil temperature value directly influences biological processes such as seed germination, microbial activity or disease pressure, as well as chemical and physical soil dynamics including nutrient availability and water movement. Thereby, in some embodiments, an output of the computer-implemented method may be used in a sub-sequent model, wherein the subsequent model configured to determine one of the following list: seed germination, microbial activity, disease pressure, nutrient dynamics, and water movement.

[0259] The computer implemented method of the second alternative aspect may further comprise the steps of:

[0260] determining, based on the DSM, a surface normal vector to a surface of the subarea

[0261] determining an irradiation estimation reaching a sub-area of the sculpted landscape, the irradiation estimation being derived from the estimated irradiation value, and wherein the estimated irradiation value comprises a combination of a direct normal irradiance dependent on an angle of incidence of sunlight with respect to said surface normal vector and a diffuse horizontal irradiance indicative of sunlight scattering.

[0262] The irradiation estimation reaching a sub-area may be at least one part of the estimated irradiation value configured to be within a sub-area of the plurality of sub-areas. Alternatively, the irradiation estimation reaching a sub-area may be an entire part of the estimated irradiation value, wherein the estimated irradiation value is configured to be adjusted with the combination of the direct normal irradiance and the diffuse horizontal irradiance.

[0263] Thereby, the irradiated estimation allows for an adjustment of the irradiation value in a sunlit (non-shaded) area to, in turn, obtain a more accurate and precise irradiation value in a sub-area. Consequently, for one or more sub-areas, the estimated irradiation value may be a result from adding the direct normal irradiance (DNI) to the diffuse horizontal irradiance (DHI).

[0264] In some implementations, the irradiation estimation reaching a sub-area of the sculpted landscape may equivalently be expressed as a global horizontal irradiance (GHI) via the following equation GHI = DNI × cos(θ) + DHI, wherein the DNI and the DHI may be obtained from a reference solar irradiation that may be comprised by the set of weather data, and (θ) is a Sun's zenith angle. Alternatively, the GHI may be directly obtained from the set of weather data.

[0265] By a surface normal vector may herein be understood a vector orthogonal and / or normal to the surface of the respective subarea. The surface normal vector may be orthogonal and / or normal to at least a part of the surface of the respective sub-area and / or may be orthogonal and / or normal to an average or smoothed surface of the respective sub-area.

[0266] The direct normal irradiance may be an amount of scattered sunlight configured to be measured at the surface of the sculpted landscape. Moreover, the direct normal irradiance may be an amount of sunlight dependent on a Sun's azimuth angle (θ). Additionally or alternatively, the diffuse horizontal irradiance may be scattered sunlight from the sky when reaching the surface of the sculped landscape, but excluding direct rays from the Sun.

[0267] In some embodiments, of the computer-implemented method of the second alternative method, wherein prior to step (e), the computer-implemented method of the first alternative method further comprises the steps of:

[0268] determining, based on the shadow value, a sunlit region and a shaded region in the one or more sub-areas of the plurality of sub-areas, wherein the determined estimated irradiation value of step (f) comprises, in each the one or more sub-areas, a first irradiation estimation determined for the sunlit region and a second irradiation estimation determined for the shaded region,

[0269] and wherein the determined estimated soil temperature value comprises

[0270] a first soil temperature estimation associated with the sunlit region and obtained by using the evapotranspiration model, the first irradiation estimation, and the set of weather data, and

[0271] a second soil temperature estimation associated with the shaded region and obtained by using the leaf surface temperature model, the second irradiation estimation, and the set of weather data.

[0272] Therefore, the first soil temperature estimation in the sunlit region may be established after determining the shadow value in each sub-area, which in turn, allows to clearly divide each sub-area in sunlit and shaded regions. Similarly, the second soil temperature estimation may be established for a shaded region. Thereby a more precise soil temperature may be obtained, such as with a higher spatial and temporal resolution.

[0273] For sub-areas where sunlit and shaded regions may be determined, the estimated irradiation value in a sunlit sub-area may be determined based on the weather data obtained, such as to provide more accurate values in the sunlit sub-area compared to an average irradiation value for an entire surface of the sculpted landscape.

[0274] A sunlit region may be a non-shaded region, or alternatively a remaining area after determination of a shaded region in a sub-area using the shadow value. A shaded region may be an area where sunlight is blocked.

[0275] In some embodiments, the sub-areas may comprise at least one portion of sunlit region, at least one portion of shaded region or a combination thereof. Additionally or alternatively, the sub-areas may span a plurality of sunlit regions and a plurality of shaded regions. In alternative embodiments, the sub-area may comprise a complete sunlit region within said sub-area or a complete shaded region within said sub-area.

[0276] For each such sunlit and shaded regions in each of the sub-areas, an estimated soil temperature value may be indicated as determined from the first and second soil temperature estimation. Additionally, or alternatively, the computer-implemented method may be configured to determine soil temperature estimations in sunlit and shaded regions.

[0277] In some embodiments, the computer-implemented method may comprise a step of obtaining a measurement of an additional soil temperature, wherein the measurement may employ sensors or probes configured to detect and report average additional soil temperature values in standardized units. Additionally or alternatively, the estimated soil temperature value may be compared to average additional soil temperature values.

[0278] Therefore, the computer-implemented method of this second alternative aspect may have a reference frame for the soil temperature value when providing an output for the estimated soil temperature value.

[0279] In some embodiments, the computer-implemented method may further comprise the steps of:

[0280] combining, for one or more of sub-areas of the plurality of the sub-areas, the estimated soil temperature value into an estimated soil temperature map of the sculpted landscape.

[0281] Consequently, the estimated soil temperature map provides an overview of a temperature distribution for the soil in an entire sculpted landscape.

[0282] The term "map" is intended to encompass any graphical, digital, or data-structured depiction of a surface, area, or landscape, wherein each region or coordinate is linked to a corresponding value. The skilled person may understand that, within the context of this disclosure, an "estimated soil temperature map" refers to a representation of spatial regions associated with one or more numerical or qualitative indicators related to the estimated soil temperature value, as determined by the second alternative aspect of this disclosure.

[0283] The estimated soil temperature map be generated by using a graphical user interface. Alternatively, or additionally, the estimated soil temperature map may be generated by overlaying the estimated soil temperature values for each of the sub-areas of the sculpted landscape onto a digital map.

[0284] In alternative implementations, the estimated soil temperature map be generated by stitching data associated with each sub-area to form a map as a graphical user interface.

[0285] In some embodiments, the computer-implemented method of the second alternative aspect further comprising the step of:

[0286] generating, for the one or more sub-areas of the plurality of sub-areas, a predictive soil temperature estimation model indicative of a future soil temperature estimation for the sculpted landscape.

[0287] Thereby, a user performing the computer implemented method of the first alternative aspect may obtain a fast and efficient answer regarding a soil temperature for a particular sub-area or an entire sculpted landscape on a predetermined future date.

[0288] A future soil temperature estimation may be associated with an evapotranspiration value in a sub-area.

[0289] A soil temperature estimation model may refer to a computational, mathematical, or algorithmic representation configured to simulate, predict, or estimate a soil temperature value based on one or more input parameters.

[0290] The soil temperature estimation model may include, but is not limited to, deterministic or probabilistic components and may utilize empirical data, theoretical relationships, or machine learning techniques to generate outputs. The outputs of the model may include predictions, risk assessments, or recommended actions, and the model may be adapted to update dynamically based on new data or changing conditions.

[0291] In some embodiments the predictive soil temperature estimation model may be generated by: processing the set of weather data using a machine learning data architecture, the machine learning data architecture being applied the soil temperature estimation model, and wherein the machine learning data architecture is trained to determine an estimated soil temperature value based on one or more of the selected list: a baseline soil temperature estimation history, a determined estimated soil temperature value history, historical weather data, forecast weather data, an irrigation input history, and soil moisture data. The machine learning (ML) data architecture may belong to a pre-existing or newly created ML architecture, e.g. the ML model may be based on neural networks, support vector machines, and / or genetic algorithms among other models comprising artificial intelligence.

[0292] The machine-learning data architecture may be trained based on a training data set comprising, e.g., an estimated soil temperature value from ten sculpted landscapes located in ten different geolocations, in each respective geolocation, 200 days of historical weather conditions, and 200 estimated soil temperature estimation values for each of the sub-areas of the plurality of sub-areas in each of the sculpted landscapes. The estimated soil temperature value in the training data may be obtained from an output of the computer-implemented method herein disclosed. Additionally or alternatively, the estimated soil temperature value in the training data set may be obtained manually based on observations from computer registrations or empirical measurements and may provide an indication of future soil temperature estimations in each said sub-area. Additionally or alternatively, the observations and parts of the information in the training data set may also be made provided by a turf manager in the sculpted landscape e.g., a groundskeeper or a greenkeeper.

[0293] A third alternative aspect of this disclosure discloses a computer-implemented method for estimating disease pressure of a sculpted landscape, such as a golf course, wherein the sculpted landscape comprises a surface and one or more objects, such as buildings or trees, and the method comprises the steps of:

[0294] a) obtaining a geolocation of the surface of the sculpted landscape

[0295] b) obtaining a digital surface model, DSM, of the sculpted landscape, wherein the DSM comprises an elevation of the surface of the sculpted landscape and dimensions of the objects raising from the surface of the sculpted landscape;

[0296] c) subdividing the surface of the sculpted landscape into a plurality of sub-areas, d) determining, for one or more of sub-areas of the plurality of the sub-areas, a shadow value indicative of an amount of sunlight incident on the respective sub-area over a predetermined time interval by a sun ray tracing model and the geolocation,

[0297] e) obtaining a set of weather data indicative of meteorological conditions for the sculpted landscape,

[0298] f) determining, for the one or more sub-areas of the plurality of sub-areas, an estimated irradiation value by using the set of weather data and the shadow value for said predetermined time interval,

[0299] g) determining, for the one or more sub-areas of the plurality of sub-areas, an estimated soil temperature value by using the estimated irradiation value and the set of weather data into a soil temperature model, the estimated soil temperature value being determined for said predetermined time interval

[0300] h) determining, for the one or more sub-areas of the plurality of sub-areas, an estimated probability of disease pressure value by using the estimated irradiation value, the estimated soil temperature value and the set of weather data into a probabilistic disease pressure model, the estimated probability of disease pressure value being determined for said predetermined time interval.

[0301] Disease pressure in this disclosure may be understood by the skilled person as a combined influence of environmental conditions, pathogen presence, and host susceptibility that determines the likelihood and severity of disease outbreaks. In sculpted landscapes such as turfgrass systems and golf courses, high disease pressure from pathogens (e.g. from a fungal disease, such as dollar spot epidemics) may lead to significant aesthetic and playability issues, as well as increased maintenance costs. The term disease pressure may further be understood by the skilled person as a value indicative of probability of disease outbreak in surface of the sculpted landscape. Additionally or alternatively, the probability of disease outbreak may be expressed as an estimated probability of disease pressure value in this disclosure.

[0302] Consequently, the computer-implemented method of this third alternative aspect allows to obtain an estimated probability of disease pressure value that may have a high spatial and temporal resolution. This may be useful for turf management forecast.

[0303] The steps a)-f) of the third alternative aspect may be similar or identical to the steps a)-f) of the method according to the first aspect of the present invention. Moreover, the step g) of this third alternative aspect may be similar or identical to step g) of the method according to the second aspect of the present invention. Correspondingly, any feature and / or embodiment described with respect to the steps a)-f) of the method according to the first aspect may equally apply method steps a)-f) of the method of this third alternative aspect. Similarly, any feature and / or embodiment related to step g) of the method in the second alternative aspect may apply to method step g) in this third alternative aspect.

[0304] The weather data may be weather data as described with respect to the method according to the first aspect. The size of the sub-areas may be size of the sub-area as described with respect to the method according to the first aspect. The predetermined time interval may be the predetermined time interval as described with respect to the method according to the first aspect. The embodiments of the steps of obtaining and modifying the DSM may be described as embodiments of steps of obtaining and modifying the DSM according to the first aspect. The steps of obtaining an estimated soil temperature value may be performed according the second alternative aspect. In particular, all embodiments related to the second alternative aspect of the invention may equally apply to the method according to the third alternative aspect.

[0305] In some embodiments, the estimated probability of disease pressure value is indicative of a risk of disease in growth of the surface, such as grass and an amount of the area of the sculpted landscape, such as a subset of sub-areas.

[0306] In some embodiments, the disease pressure may refer to risk of diseases such as fungal caused diseases, such as dollar spot. In some embodiments, the disease pressure may be or comprise one or more disease pressure values, each disease pressure value indicative of a risk of a respective disease. The diseases may, for instance, be one or more of Dollar Spot, Brown Patch, Pythium Blight, Microdochium Patch (or Fusarium Patch), Anthracnose, Snow Mould, Take-All Patch, Fairy Ring, Leaf Spot (or Melting-Out), and Summer Patch.

[0307] In some embodiments, the predetermined time interval, from step d), comprises an acquisition data period and a predictive time period, the acquisition data period selected from a range between the acquisition data period selected from a range between a 15 minutes and one hour and the predictive time period selected from a range between one day and 14 days. In some embodiments, the probabilistic disease pressure model is associated with the Smith-Kerns dollar spot model and the estimated probability of disease pressure value may be indicative of a dollar spot epidemic. In an additional implementation, the predetermined time interval may be a five day moving average, and the set of weather parameters may comprise a five day moving average of relative humidity and a daily average of air temperature. The predetermined time interval may be selected dependent on the disease, for which a disease pressure is to be determined.

[0308] The Smith-Kerns dollar spot model has been proved to be effective in supressing the fungal epidemic of dollar spots on golf courses, thereby providing a useful application for the present method of the third alternative aspect. Moreover, the Smith-Kerns dollar spot model may provide for each sub-area an estimated probability of disease pressure value having a higher spatial resolution and precision compared to the Smith-Kerns dollar spot model used on an entire surface of the sculpted landscape.

[0309] In some embodiments, the computer-implemented method is generated by processing the set of weather data using a machine learning data architecture, the machine learning data architecture being applied the disease pressure model, and wherein the machine learning data architecture is trained to determine an estimated disease pressure value based on one or more of the selected list: a baseline disease pressure history, a determined estimated disease pressure history, historical weather data, forecast weather data, an irrigation input history, and soil moisture data.

[0310] The machine-learning data architecture may be trained based on a training data set comprising, e.g., for each disease and for ten sculpted landscapes at ten different geolocations, a respective geolocation, 200 days of historical weather conditions, and 200 estimated probability of disease pressure values for each of the sub-areas of each of the sculpted landscapes. The estimated probability of disease pressure values in the training data set may be obtained manually based on observations and may be an indication of a development or risk of the disease in the sub-area. The observation may be made by, e.g., a groundskeeper or a greenkeeper. The machine-learning data architecture may be trained based on a plurality of diseases.

[0311] A second aspect of the present invention relates to an irrigation system comprising an irrigation device and a control unit configured to control the irrigation device, the control unit being configured to carry out the steps of the method according to the first aspect.

[0312] In this manner, the irrigation system may be designed as an automated irrigation control system to provide for accurate irrigation amounts while being adapted to cover one or more of the plurality of sub-areas of the sculpted landscape.

[0313] The irrigation device may be operably connected to the control unit. The control unit may be configured to control the irrigation device by carrying out the steps of the method as well as determining, for one or more sub-areas of the plurality of sub-areas, an estimated irrigation value required in the sub-area of the surface of the sculpted landscape based on the estimated evapotranspiration value.

[0314] The irrigation device may be configured to apply water to one or more sub-areas of the plurality of subareas. For instance, the irrigation device may be configured to apply water corresponding to the estimated irrigation value for any one or more sub-areas of the plurality of sub-areas of the surface of the sculpted landscape.

[0315] The control unit may be configured to control the irrigation device based on the estimated irrigation value. For instance, the control unit may be configured to control the irrigation device to provide an amount of water corresponding to and / or indicated by the estimated irrigation value the one or more sub-areas.

[0316] The irrigation system may further comprise a memory operably connected to the control unit. The memory may be configured to store thereon instructions causing the control unit to perform the method according to the first aspect as well as, determining, for one or more sub-areas of the plurality of sub-areas, an estimated irrigation value required in the sub-area of the surface of the sculpted landscape based on the estimated evapotranspiration value, and controlling the irrigation device based on the estimated irrigation value.

[0317] Additionally, or alternatively, the irrigation system may comprise an irrigation device, such as fluid supply conduit operatively connected to a pressurized water source and a plurality of discharge elements arranged along the conduit. Each discharge element may include a flow-regulating mechanism adapted to maintain a substantially uniform output regardless of variations in upstream pressure. The irrigation system may then be programmed to follow instructions from the computer implemented method herein disclosed in the first aspect of this disclosure. In some embodiments, the irrigation system may be a GPS sprayer system configured to allocate one or more sub-areas of the surface of the sculpted landscape to an assigned irrigation device that is closest to said sub-area.

[0318] In a further aspect, the present invention relates to a system comprising a control unit configured to carry out the steps of any one of the methods according the first alternative aspect, the second alternative aspect, or the third alternative aspect.

[0319] According to a third aspect, the present invention relates to a computer program product comprises instructions, which when executed by a computer, causing the computer to carry out the steps of the method according to the first aspect, the first alternative aspect, the second alternative aspect, or the third alternative aspect.

[0320] The computer program product may further comprise a non-transitory computer-readable medium having stored thereon instructions comprising steps of the method according to the method according to the first aspect, the first alternative aspect, the second alternative aspect, or the third alternative aspect, respectively.

[0321] Further disclosed is a computer-readable data carrier having stored thereon the computer program product according to the third aspect.

[0322] The computer programme product according to the third aspect may provide any advantage and / or comprise any feature described with respect to the first aspect, the first alternative aspect, the second alternative aspect, or the third alternative aspect, respectively.

[0323] Presently preferred embodiments and further advantages will be apparent from the subsequent detailed description and drawings. A person skilled in the art will appreciate that any one or more of the above aspects of this disclosure and embodiments thereof may be combined with any one or more of the other aspects of the disclosure and embodiments.

[0324] Brief Description of Drawings

[0325] In the following description, embodiments will be described with reference to the schematic drawings, in which:

[0326] FIG. 1 shows a flow chart of an embodiment of a computer-implemented method for estimating evapotranspiration of a sculpted landscape; FIG. 2 shows a flow chart of an embodiment of a computer-implemented method for estimating a surface temperature of a sculpted landscape;

[0327] FIG. 3 shows a flow chart of an embodiment of a computer-implemented method for estimating a soil temperature of a sculpted landscape;

[0328] FIG. 4 shows a flow chart of an embodiment of a computer-implemented method for estimating for estimating disease pressure of a sculpted landscape; and

[0329] FIG. 5 shows a schematic block diagram of an embodiment of an irrigation system. FIG. 6 shows a system architecture diagram showing the integration of the data acquisition module, ET modelling unit, irrigation optimization engine, irrigation control system, and visualization platform

[0330] FIG. 7 shows a dynamic shading analysis workflow, illustrating the generation of shadow maps and irradiation maps using DSM data and sun position inputs FIG. 8 shows an irrigation optimization workflow, and processing from data acquisition to water input recommendations and irrigation control

[0331] Similar reference numerals are used for similar elements across the various embodiments and figures described herein.

[0332] Description of Embodiments

[0333] The present invention will now be described in more detail hereinafter with reference to the accompanying drawings, in which an embodiment of the invention is shown. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided for thoroughness and completeness.

[0334] Referring initially to FIG 1, FIG. 1 illustrates a flow chart of an embodiment of a computer-implemented method 1 for estimating evapotranspiration of a sculpted landscape. The sculpted landscape comprises a surface and one or more objects, such as buildings or trees.

[0335] The method 1 comprises the step of obtaining 10 a geolocation of the surface of the sculpted landscape. The method 1 further comprises the step of obtaining 11 a digital surface model, DSM, of the sculpted landscape, wherein the DSM comprises an elevation of the surface of the sculpted landscape and dimensions of the objects raising from the surface of the sculpted landscape. The method 1 furthermore comprises the step of subdividing 12 the surface of the sculpted landscape into a plurality of sub-areas and the step of determining 13, for one or more of sub-areas of the plurality of the sub-areas, a shadow value indicative of an amount of sunlight incident on the respective sub-area over a predetermined time interval by a sun ray tracing model and the geolocation.

[0336] Furthermore, the method 1 comprises the step of obtaining 14 a set of weather data indicative of meteorological conditions for the sculpted landscape and determining 15, for the one or more sub-areas of the plurality of sub-areas, an estimated irradiation value by using the set of weather data and the shadow value for said predetermined time interval.

[0337] The method 1 moreover comprises the step of determining 16, for the one or more sub-areas of the plurality of sub-areas, an estimated evapotranspiration value by using the estimated irradiation value and the set of weather data into an evapotranspiration model, the estimated evapotranspiration value being determined for said predetermined time interval.

[0338] While steps 10, 11, 12, 13, 14, and 15 are illustrated subsequently in FIG. 1, it will be appreciated that the steps may be performed in parallel or in a different order. For instance, the step of obtaining 14 the weather data may be performed prior to or in parallel with any one of steps 10-13. Alternatively or additionally, the step of obtaining 10 the geolocation may be performed in parallel with any one of steps 11-14.

[0339] FIG. 2 shows a flow chart of an embodiment of a computer-implemented method 2 for estimating a surface temperature of a sculpted landscape.

[0340] The computer-implemented method 2 is for estimating a surface temperature of a sculpted landscape, such as a golf course, wherein the sculpted landscape comprises a surface and one or more objects, such as buildings or trees. The method 2 comprises the steps of obtaining 20 a geolocation of the surface of the sculpted landscape, and obtaining 21 a digital surface model, DSM, of the sculpted landscape, wherein the DSM comprises an elevation of the surface of the sculpted landscape and dimensions of the objects raising from the surface of the sculpted landscape.

[0341] The method 2 further comprises subdividing 22 the surface of the sculpted landscape into a plurality of sub-areas, and determining 23, for one or more of sub-areas of the plurality of the sub-areas, a shadow value indicative of an amount of sunlight incident on the respective sub-area over a predetermined time interval by a sun ray tracing model and the geolocation.

[0342] The method 2 moreover comprises the step of obtaining 24 a set of weather data indicative of meteorological conditions for the sculpted landscape.

[0343] Subsequently, the method comprises determining 25, for the one or more sub-areas of the plurality of sub-areas, an estimated irradiation value by using the set of weather data and the shadow value for said predetermined time interval and determining 26, for the one or more sub-areas of the plurality of sub-areas, an estimated soil temperature value by using the estimated irradiation value and the set of weather data into a leaf surface temperature model, the estimated surface temperature value being determined for said predetermined time interval.

[0344] The steps 20, 21, 22, 23, 24, and 25 are identical to steps 10, 11, 12, 13, 14, and 15, respectively, of the method 1 shown in FIG. 1.

[0345] While steps 20, 21, 22, 23, 24, and 25 are illustrated subsequently in FIG. 2, it will be appreciated that the steps may be performed in parallel or in a different order. For instance, the step of obtaining 24 the weather data may be performed prior to or in parallel with any one of steps 20-23. Alternatively or additionally, the step of obtaining 20 the geolocation may be performed in parallel with any one of steps 21-24.

[0346] FIG. 3 shows a flow chart of an embodiment of a computer-implemented method 3 for estimating a soil temperature of a sculpted landscape, such as a golf course, wherein the sculpted landscape comprises a surface and one or more objects, such as buildings or trees. The method 3 comprises the steps of: obtaining 30 a geolocation of the surface of the sculpted landscape, obtaining 31 a digital surface model, DSM, of the sculpted landscape, wherein the DSM comprises an elevation of the surface of the sculpted landscape and dimensions of the objects raisingfrom the surface of the sculpted landscape, and subdividing 32 the surface of the sculpted landscape into a plurality of sub-areas.

[0347] The method 3 further comprises the step of determining 33, for one or more of subareas of the plurality of the sub-areas, a shadow value indicative of an amount of sunlight incident on the respective sub-area over a predetermined time interval by a sun ray tracing model and the geolocation.

[0348] The method further comprises the step of obtaining 34 a set of weather data indicative of meteorological conditions for the sculpted landscape. The method 3 moreover comprises determining 35, for the one or more sub-areas of the plurality of sub-areas, an estimated irradiation value by using the set of weather data and the shadow value for said predetermined time interval, and determining 36, for the one or more sub-areas of the plurality of sub-areas, an estimated soil temperature value by using the estimated irradiation value and the set of weather data into a soil temperature model, the estimated surface temperature value being determined for said predetermined time interval.

[0349] The steps 30, 31, 32, 33, 34, and 35 are identical to steps 10, 11, 12, 13, 14, and 15, respectively, of the method 1 shown in FIG. 1.

[0350] While steps 30, 31, 32, 33, 34, and 35 are illustrated subsequently in FIG. 3, it will be appreciated that the steps may be performed in parallel or in a different order. For instance, the step of obtaining 34 the weather data may be performed prior to or in parallel with any one of steps 30-33. Alternatively or additionally, the step of obtaining 30 the geolocation may be performed in parallel with any one of steps 31-34.

[0351] FIG. 4 shows a flow chart of an embodiment of a computer-implemented method 4 for estimating disease pressure of a sculpted landscape, such as a golf course, wherein the sculpted landscape comprises a surface and one or more objects, such as buildings or trees. The method 4 comprises the steps of: obtaining 40 a geolocation of the surface of the sculpted landscape, and obtaining 41 a digital surface model, DSM, of the sculpted landscape, wherein the DSM comprises an elevation of the surface of the sculpted landscape and dimensions of the objects raisingfrom the surface of the sculpted landscape.

[0352] The method 4 further comprises the steps of subdividing 42 the surface of the sculpted landscape into a plurality of sub-areas, determining 43, for one or more of subareas of the plurality of the sub-areas, a shadow value indicative of an amount of sunlight incident on the respective sub-area over a predetermined time interval by a sun ray tracing model and the geolocation, and obtaining 44 a set of weather data indicative of meteorological conditions for the sculpted landscape.

[0353] Furthermore, the method 4 comprises the steps of determining 45, for the one or more sub-areas of the plurality of sub-areas, an estimated irradiation value by using the set of weather data and the shadow value for said predetermined time interval, and determining 46, for the one or more sub-areas of the plurality of sub-areas, an estimated soil temperature value by using the estimated irradiation value and the set of weather data M

[0354] into a soil temperature model, the estimated surface temperature value being determined for said predetermined time interval.

[0355] Moreover, the method 4 comprises determining 47, for the one or more sub-areas of the plurality of sub-areas, an estimated probability of disease pressure value by using the estimated irradiation value, the estimated soil temperature value and the set of weather data into a probabilistic disease pressure model, the estimated probability of disease pressure value being determined for said predetermined time interval.

[0356] The steps 40, 41, 42, 43, 44, and 45 are identical to steps 10, 11, 12, 13, 14, and 15, respectively, of the method 1 shown in FIG. 1.

[0357] While steps 40, 41, 42, 44, 44, and 45 are illustrated subsequently in FIG. 4, it will be appreciated that the steps may be performed in parallel or in a different order. For instance, the step of obtaining 44 the weather data may be performed prior to or in parallel with any one of steps 40-44. Alternatively or additionally, the step of obtaining 40 the geolocation may be performed in parallel with any one of steps 41-44.

[0358] FIG. 5 shows a schematic block diagram of an embodiment of an irrigation system 5. The irrigation system 5 comprises a control unit 50 and an irrigation device 51 operably connected to the control unit 50. The control unit is configured to control the irrigation system 51, by carrying out the steps of the method 1 as well as determining, for one or more sub-areas of the plurality of sub-areas, an estimated irrigation value required in the sub-area of the surface of the sculpted landscape based on the estimated evapotranspiration value. The irrigation device 51 is configured to apply water corresponding to the estimated irrigation value for any one or more sub-areas of the plurality of sub-areas of the surface of the sculpted landscape. The control unit is configured to control the irrigation device 51 based on the estimated irrigation value. In particular, the control unit 50 is configured to control the irrigation device 51 to provide an amount of water corresponding to and / or indicated by the estimated irrigation value the one or more sub-areas.

[0359] The irrigation system 5 further comprises a memory 52 operably connected to the control unit 50. The memory 52 is configured to store thereon instructions causing the control unit 50 to perform the method 1, determining, for one or more sub-areas of the plurality of sub-areas, an estimated irrigation value required in the sub-area of the surface of the sculpted landscape based on the estimated evapotranspiration value, and controlling the irrigation device 51 based on the estimated irrigation value.

[0360] The present disclosure is intended to be described by the general inventive concept, and by referring to specific embodiments and examples, including those shown in the accompanying drawings and in the Enumerated Exemplary Embodiments (EEE). The invention should, however, not be construed as limited to the specific embodiments, examples and EEE set forth herein.

[0361] In one example, the technical problem addressed is the inaccurate estimation of evapotranspiration and inefficient irrigation caused by coarse models that fail to account for local shading, weather variations, and soil properties. Existing models typically generalize ET estimations across larger areas without accounting for microscale variances, leading to discrepancies in water application and plant health outcomes. Furthermore, current irrigation systems often rely on manual operations or simplistic automation, lacking integration with dynamic, high-resolution environmental data. In this example, this is solved these issues by providing precise ET calculations at a resolution of 1 square meter, enabling highly localized insights into water requirements. The present example employs advanced digital surface modelling (DSM) techniques, combined with dynamic shading analysis and real-time microclimatic data, to generate spatially and temporally resolved ET maps. By leveraging lidar-based DSM data collected via drones, planes, or satellites, the system calculates hourly solar irradiation and shadow distributions for every square meter of land. These data are then integrated into ET calculations using the FAO-56 Penman- Monteith method, ensuring an accurate assessment of water loss across microclimates.

[0362] Moreover, the present example incorporates machine learning predictions trained on historical weather patterns, soil moisture levels, and crop-specific data. This predictive capability allows for anticipatory irrigation adjustments, ensuring optimal water usage before plant stress occurs. The system's ability to integrate real-time data with predictive modelling ensures flexibility for both automated and manual irrigation, enhancing water conservation efforts while maintaining plant health.

[0363] Existing solutions also fail to adapt efficiently to complex terrains, such as golf courses or agricultural fields with variable vegetation and structural elements. Localized shading caused by trees, slopes, or man-made structures can significantly alter ET values. The present example's dynamic shading analysis addresses this gap by generating detailed shadow maps at hourly intervals, allowing irrigation systems to adjust water application precisely according to site-specific conditions. Additionally, the system in the present example provides actionable recommendations in millimeters or equivalent units, facilitating easy interpretation and implementation by end users.

[0364] Overall, the present example improves the accuracy, efficiency, and flexibility of irrigation systems, addressing key challenges associated with water scarcity, energy efficiency, and sustainable resource management in turf care, agriculture, and similar industries.

[0365] In a further alternative or additional example, a system is disclosed as outlined in FIG.

[0366] 6. The system may comprise parts A, B, C, D and E (see Figure 6), with advantages and capabilities as set forth below:

[0367] A. Data Acquisition Module:

[0368] Collects microclimatic, soil, water quality, real-time weather, and crop-specific data.

[0369] Real-time weather data is sourced from satellites, local weather stations, or similar sources.

[0370] Additional sources include ground-based sensors and high-resolution digital surface models (DSM).

[0371] DSMs are obtained using lidar technology deployed via drones, planes, satellites, or similar platforms to ensure accurate topographical and structural information. Integrates remote sensing technologies (e.g., NDVI, hyperspectral) to assess vegetation health.

[0372] B. Evapotranspiration Modeling Unit:

[0373] Implements the FAO-56 Penman-Monteith equation to calculate hourly reference evapotranspiration (ET0).

[0374] Uses crop coefficients to derive crop evapotranspiration (ETc).

[0375] Incorporates dynamic shading analysis by (see FIG. 7):

[0376] - Generating shadow maps from DSM files using sun position data (elevation, azimuth).

[0377] - Computing irradiation maps by integrating shadow maps with weather data-provided solar radiation. - Producing hourly ETc maps through element-wise operations at a resolution of 1 square meter.

[0378] Integrates energy balance principles, accounting for net radiation, sensible heat flux, latent heat flux, and ground heat flux.

[0379] Incorporates machine learning models for future ET predictions and irrigation optimization.

[0380] Uses crop-specific growth models for tailored irrigation scheduling.

[0381] Aggregates hourly ETc maps into daily spatial ETc maps for actionable irrigation insights.

[0382] C. Irrigation Optimization Engine (see FIG. 8):

[0383] Adapts to rainfall events, vegetation health data, and other environmental changes in real time.

[0384] Calculates the optimal irrigation amount based on ETc maps and crop-specific parameters.

[0385] Incorporates machine learning models to increase optimize suggested irrigation amount.

[0386] Transfers ETc data to smart irrigation systems, enabling precise irrigation scheduling and water application based on real-time environmental conditions. D. Irrigation Control System:

[0387] Automates water delivery through smart irrigation infrastructure, including valves, pumps, and sensors.

[0388] Allows for manual intervention or adjustment as required based on

[0389] the system's water input recommendations.

[0390] Provides end-users with precise water input recommendations expressed in millimeters or other equivalent variables.

[0391] E. Visualization Platform:

[0392] Provides end-users with actionable insights, including ETc maps, irrigation schedules, and vegetation health analyses.

[0393] Displays water input recommendations in a user-friendly format, expressed in millimeters or other equivalent units.

[0394] Allows users to monitor system performance, environmental conditions, and irrigation control operations in real time. In a further alternative or additional example, the following Enumerated Exemplary Embodiments (EEEs) are presented and outlined below:

[0395] 1. An automated and manual irrigation management system comprising:

[0396] A data acquisition module to collect microclimatic, weather, soil, and cropspecific data, including digital surface model (DSM) data collected via lidar technology from drones, planes, or satellites;

[0397] An evapotranspiration modeling unit configured to calculate reference evapotranspiration (ET0) and crop evapotranspiration (ETc), incorporating dynamic shading analysis, wherein digital surface models (DSM) are used to generate shadow maps by integrating sun position data (elevation, azimuth) and hourly solar radiation inputs. The shadow maps are combined with weatherbased irradiation data to produce hourly irradiation maps, which are used to adjust ETc calculations at a resolution down to 1 square meter for precise irrigation insights;

[0398] A machine learning module to predict future water needs based on historical data;

[0399] An irrigation optimization engine to generate precise water input recommendations in millimeters or other equivalent variables

[0400] An irrigation control system to deliver water via automated or manual irrigation systems;

[0401] A remote sensing unit for analyzing vegetation health via indices such as NDVI or hyperspectral imaging to dynamically adjust irrigation schedules;

[0402] A visualization platform providing actionable insights and irrigation recommendations;

[0403] 2. The system of EEE 1, wherein digital surface models are generated via lidar data collected using drones, planes, or satellites.

[0404] 3. The system of EEE 1, wherein the dynamic shading analysis incorporates hourly sun position data and adjusts for seasonal changes in solar elevation and azimuth to ensure accuracy across different climatic conditions. 4. The system of EEE 1, further comprising a module for calculating soil moisture dynamics across multiple soil layers by integrating soil infiltration rates, water retention curves, and thermal properties.

[0405] 5. The system of EEE 1, wherein the machine learning module predicts long term irrigation requirements by analyzing historical environmental data, crop growth patterns, and forecasted weather data.

[0406] 6. The system of EEE 1, wherein the system integrates crop-specific growth models to optimize irrigation schedules.

[0407] 7. The system of EEE 1, wherein the system generates daily ETc maps by aggregating hourly ETc calculations to provide spatially resolved irrigation insights.

[0408] 8. The system of EEE 1, further comprising an alert system that notifies users of deviations in ETc levels, soil moisture content, or vegetation health thresholds.

[0409] 9. The system of EEE 1, wherein the irrigation control system incorporates energy-efficient technologies such as solar-powered pumps or variable rate irrigation systems.

[0410] 10. The system of EEE 1, wherein the solution can be deployed on cloud infrastructure or on-premises systems based on user preference for data management and control.

Claims

Claims1. A computer-implemented method for estimating evapotranspiration of a sculpted landscape, such as a golf course, wherein the sculpted landscape comprises a surface and one or more objects, such as buildings or trees, and the method comprises the steps of:a) obtaining a geolocation of the surface of the sculpted landscapeb) obtaining a digital surface model, DSM, of the sculpted landscape, wherein the DSM comprises an elevation of the surface of the sculpted landscape and dimensions of the objects raising from the surface of the sculpted landscape;c) subdividing the surface of the sculpted landscape into a plurality of sub-areas, d) determining, for one or more of sub-areas of the plurality of the sub-areas, a shadow value indicative of an amount of sunlight incident on the respective sub-area over a predetermined time interval by a sun ray tracing model and the geolocation,e) obtaining a set of weather data indicative of meteorological conditions for the sculpted landscape,f) determining, for the one or more sub-areas of the plurality of sub-areas, an estimated irradiation value by using the set of weather data and the shadow value for said predetermined time interval,g) determining, for the one or more sub-areas of the plurality of sub-areas, an estimated evapotranspiration value by using the estimated irradiation value and the set of weather data into an evapotranspiration model, the estimated evapotranspiration value being determined for said predetermined time interval.

2. A computer-implemented method according to claim 1, wherein the method further comprises the steps of:determining, based on the DSM, a surface normal vector to a surface of the subareadetermining an irradiation estimation reaching a sub-area of the sculpted landscape, the irradiation estimation being derived from the estimated irradiation value, and wherein the irradiation estimation comprises a direct normal irradiance dependent on an angle of incidence of sunlight with respect to the surface normal vector and a diffuse horizontal irradiance originating from light scattering.

3. The computer-implemented method according to claim 1 or 2, wherein prior to step (e), the method further comprises the steps of:determining, based on the shadow value, a sunlit region and a shaded region in the one or more sub-areas of the plurality of sub-areas,wherein the determined estimated irradiation value of step (f) comprises, in each the one or more sub-areas, a first irradiation estimation determined for the sunlit region and a second irradiation estimation determined for the shaded region,and wherein the determined estimated evapotranspiration value comprisesa first evapotranspiration estimation associated with the sunlit region and obtained by using the evapotranspiration model, the first irradiation estimation, and the set of weather data, anda second evapotranspiration estimation associated with the shaded region and obtained by using the evapotranspiration model, the second irradiation estimation, and the set of weather data.

4. The computer-implemented method according to any one of the preceding claims, further comprising the steps of:combining, for one or more of sub-areas of the plurality of the sub-areas, the estimated evapotranspiration value into an estimated evapotranspiration map of the sculpted landscape.

5. The computer-implemented method according to any one of the preceding claims, further comprising the steps of:h) obtaining, for the one or more sub-areas of the plurality of sub-areas, a sub-area crop coefficient,i) determining, for the one or more sub-areas of the plurality of sub-areas, an estimated crop evapotranspiration value by using the estimated evapotranspiration value and the sub-area crop coefficient into a crop evapotranspiration model, the estimated crop evapotranspiration value being determined for said predetermined time interval.

6. The computer-implemented method according to any one of the preceding claims, wherein the evapotranspiration model is a reference evapotranspiration model, and wherein determining estimated evapotranspiration value comprises the steps of:providing the estimated irradiation value and the set of weather data to the reference evapotranspiration model, thereby determining a reference evapotranspiration value ETO.

7. The computer-implemented method according to claims 5 and 6, wherein determining the estimated crop evapotranspiration value comprises the steps of:providing the reference evapotranspiration ETO and the sub-area crop coefficient to the crop evapotranspiration model, thereby determining the crop evapotranspiration value ETc by ETc=Kc·ET08. The computer-implemented method, according to any one of the preceding claims, wherein the method further comprises the step of:updating dynamically, upon the predetermined time interval, the estimated evapotranspiration value for the one or more sub-areas of the plurality of sub-areas.

9. The computer-implemented method according to any one of the preceding claims, wherein the predetermined time interval, from step d) of claim 1, comprises an acquisition data period and a predictive time period, the acquisition data period selected from a range between a 15 minutes and one hour and the predictive time period selected from a range between one day and 14 days.

10. The computer-implemented method according to any one of the preceding claims, wherein each sub-area comprises a predetermined mesh element configured to be the equal across all plurality of sub-areas, and wherein a size of the mesh element for each of the plurality of areas is between 0.05 m2and 20 m2, and preferably between 5 to 10 m2.

11. The computer-implemented method, according to any one of the preceding claims, further comprises the steps of:receiving input from a user indicating an alteration in the dimensions of any one or more objects raising from the surface of the sculpted landscape,modifying the DSM of the sculpted landscape into an altered DSM based on said input from the user,repeating at least steps d), f) and g) based on the altered DSM.

12. The computer-implemented method, according to any one of the preceding claims, further comprises the steps of:obtaining an updated digital surface model, DSM, of the sculpted landscape, wherein the DSM comprises an alteration in the dimensions of any one or more objects raising from the surface of the sculpted landscape;replacing the DSM of the sculpted landscape by the updated DSM,repeating at least steps d), f) and g) based on the altered DSM.

13. The computer-implemented method, according to any of the preceding claims, further comprising the step of:generating, for the one or more sub-areas of the plurality of sub-areas, a predictive evapotranspiration estimation model indicative of future irrigation needs for the sculpted landscape.

14. The computer-implemented method, according to claim 13, wherein the predictive evapotranspiration estimation model is generated by:processing the set of weather data using a machine learning data architecture, the machine learning data architecture being applied the evapotranspiration model, and wherein the machine learning data architecture is trained to determine an estimated evapotranspiration value based on one or more of the selected list: a baseline evapotranspiration history, a determined estimated evapotranspiration history, historical weather data, forecast weather data, an irrigation input history, and soil moisture data.

15. The computer-implemented method, according to any of the preceding claims, the method further comprising the steps of:determining, for one or more sub-areas of the plurality of sub-areas, a surface temperature value based on a leaf temperature model, wherein the leaf temperature model is configured to receive the set of weather data and the estimated irradiation value in the one or more sub-areas.

16. The computer-implemented method, according to any of the preceding claims, the method further comprising the steps of:determining, for one or more sub-areas of the plurality of sub-areas, a soil temperature value based on a soil temperature model, wherein the soil temperature model is configured to receive the estimated irradiation value in the one or more sub-areas.

17. The computer-implemented method, according to claim 16, the method further comprising the steps of:determining, for the one or more sub-areas of the plurality of sub-areas, a probability for pathogenic infection presence in the surface of the sculped landscape by using a predictive turf disease model, wherein the predictive turf disease model is configured to receive the set of weather data, the estimated irradiation value, and the surface temperature value in the one or more sub-areas.

18. The computer-implemented method, according to any one of the preceding claims, wherein the set of weather parameters indicative of meteorological conditions for the sculpted landscape comprise:an averaged air temperature,an averaged relative humidity,a measured averaged wind speed above a predetermined height over the surface sculpted landscape,a measured fraction of the sky covered with cloudsdiffuse horizontal irradiancedirect beam irradianceglobal horizontal irradiance.

19. The computer-implemented method, according to any of the preceding claims, the method further comprising the steps of:determining, for one or more sub-areas of the plurality of sub-areas, an estimated irrigation value required in the sub-area of the surface of the sculpted landscape based on the estimated evapotranspiration value.

20. The computer-implemented method, according to claim 19, further comprising the steps of:receiving, for one or more sub-areas of the plurality of sub-areas, a predetermined threshold evapotranspiration value from a user,comparing, for one or more sub-areas of the plurality of sub-areas, the estimated evapotranspiration value to the predetermined threshold evapotranspiration value, determining by said comparison, for the one or more sub-areas of the plurality of sub-areas, a target irrigation value indicative of an estimated irrigation value.

21. The computer-implemented method according to any one of claims 19 or 20, the method further comprising the steps of:controlling an irrigation device configured to apply water corresponding to the estimated irrigation value for any one or more sub-areas of the plurality of sub-areas of the surface of the sculpted landscape.

22. An irrigation system comprising an irrigation device and a control unit configured to control the irrigation device, the control unit being configured to carry out the steps of the method according to claim 21.

23. A computer program product comprising instructions, which when executed by a computer, cause the computer to carry out the steps of the method according to any one of claims 1 to 21.

24. A computer-readable data carrier having stored thereon the computer program product of claim 23.

Images