Preventive, predictive and prescriptive analysis process for precision agriculture

Abstract

The purpose of the invention is to optimise the analysis of plant, water and soil samples sent by producers to laboratories, using artificial intelligence to enhance agricultural management, using a wider dataset than in traditional agricultural management. The invention analyses physical, chemical and biological variables of the studies and compares them with the weather history and production objectives. Potential cultivation problems are identified, the most critical problems are prioritised, and action plans balancing all the variables involved in growing the plant are proposed, thereby reducing the use of fertilisers and agrochemicals. The data are captured every 15 minutes on the piece of land, enabling continuous adjustments in relation to the soil, irrigation and the plant. The invention generates customised plans for nutrition, fertility, irrigation, pests and diseases, providing specific recommendations to maximise the yield, quality, profitability and sustainability of agricultural production.

Description

[0001] PREVENTIVE, PREDICTIVE AND PRESCRIPTIVE ANALYSIS PROCESS FOR PRECISION AGRICULTURE

[0002] TECHNICAL FIELD OF THE INVENTION

[0003] The present invention relates to the technical field of precision agriculture, computer systems programmed with operations useful in agricultural management, computer systems that are programmed or configured to generate what the possible problems that the crop will have during the production cycle are and prioritize them to indicate what the action plan is to address them, and specifically to a predictive and prescriptive analysis process implementing the use of artificial intelligence to extract and analyze atmospheric weather information (historical, present and forecast), correlated with the physical, chemical and biological variables from laboratory studies related to soil, water, plant and microbiology to detect physiological and metabolic problems in the crop, as well as the real-time analysis of the interaction of representative variables of the Plant, Water, Soil and Atmospheric Weather (historical,(present and forecast) with the purpose of increasingly understanding the functioning of nature in the interaction of these variables.

[0004] Prescriptive analysis is used to generate personalized recommendations for agricultural inputs to achieve the performance, quality, profitability and sustainability objectives of the agricultural production unit.

[0005] BACKGROUND OF THE INVENTION

[0006] Precision agriculture has emerged as an advanced practice in the agricultural sector, based on the incorporation of technologies such as remote sensing, data analysis, and geographic information systems (GIS) to improve decision-making. This discipline uses detailed data on soil conditions, climate, humidity, topography, and other environmental factors to manage crops with greater precision. With the development of new predictive and prescriptive analysis techniques, farmers can now anticipate events and make optimal decisions about managing their crops and land, reducing costs, increasing productivity, and conserving natural resources.

[0007] Predictive analytics in precision agriculture refers to the use of large volumes of data, often in real time, to predict future crop scenarios. Through machine learning algorithms and advanced statistical techniques, it is possible to accurately forecast critical factors such as crop yield, potential pests, soil nutrient and moisture levels, and even weather conditions. This predictive capability not only helps optimize crop planning but also allows for minimizing climate risks and improving the management of water and fertilizer resources.

[0008] Prescriptive analytics, on the other hand, goes a step further, not only predicting outcomes but also recommending specific actions based on previous analyses. Prescriptive systems in precision agriculture analyze large volumes of historical and current data to suggest optimized interventions, such as the best time to sow, the optimal amount of fertilizers or pesticides to apply, and the most suitable irrigation techniques. This approach facilitates more informed decision-making, tailored to the specific conditions of each agricultural plot.

[0009] Advances in sensor, drone, and satellite technologies have greatly contributed to the development of predictive and prescriptive analytics in precision agriculture. These devices collect detailed, georeferenced information that enables high-resolution analysis, providing a holistic view of crop and soil health. Combined with the use of artificial intelligence (AI), farmers can efficiently manage large areas of farmland, optimizing resource use and improving the sustainability of the agricultural sector.

[0010] Predictive and prescriptive analytics are key components of modern precision agriculture, enabling data-driven management and providing farmers with a competitive advantage. These tools not only maximize crop yields but also help address challenges related to climate change, resource scarcity, and global food demand.

[0011] Currently, there are various technologies being applied to improve production processes in agriculture. All these technologies have a common objective: "To help the farmer improve food production in the crop he manages."

[0012] Mexican patent application number MX / a / 2023 / 000724, entitled "PREDICTION OF HORTICULTURAL YIELD FROM FIELD LOCATION USING MULTIBAND AERIAL IMAGES," describes its main objective as helping farmers predict crop yields by processing multiband aerial images that feed a machine learning system. This system compares current fruit growth with a historical database of pre-labeled images to predict the potential yield at harvest. Based on the information contained in the aerial images, and by analyzing the colorimetry that highlights the color range, the presence of certain elements, such as nitrogen, can be inferred. Based on this information, the system can advise farmers on whether or not to apply fertilizers.The technology described in Mexican patent application number MX / a / 2023 / 000724 is reactive to agronomic damage, as it measures the effects the plant expresses due to a lack or excess of nutrition. Reactive agronomic management can waste up to 60% of the plant's genetic potential.

[0013] Another technology is described in Indian application number IN202441030938A, titled "IoT-ENABLED SMART AGRICULTURE SOLUTION FOR PRECISION AGRICULTURE." This technology's main objective is to help farmers make decisions based on data collected by sensors installed at measuring stations. These sensors measure representative variables such as humidity, temperature, electrical conductivity, and nutrients, among others. The information measured by the sensors is sent to the cloud and displayed on a dashboard where farmers can access the data. For example, if the sensor detects low humidity, it recommends irrigation; if the sensor detects low nutrient levels, it recommends fertilizer application.The technology described in Indian application number IN202441030938A is preventative to agronomic damage, as it measures representative variables in real time; however, direct measurement of variables is not sufficient.

[0014] While all technologies have focused on telling the farmer "What to add?", the technology of the present invention focuses on helping the farmer detect "What should be eliminated?" from their production process to achieve the goal of "producing more with less" by understanding the physiological and metabolic constraints that arise from the soil, water, and biological conditions where their crop is located. A further advantage of the present invention over the disadvantages of the prior art is that it is preventive, predictive, and prescriptive, taking into account the interaction of representative variables of the plant, water, soil, and weather.

[0015] OBJECT OF THE INVENTION

[0016] The present invention aims to ensure that when a farmer begins their cultivation cycle, they always conduct a "soil, plant, water, and / or microbiology study." The invention utilizes artificial intelligence to extract and analyze information on physical, chemical, and biological variables from laboratory studies related to soil, water, plants, and microbiology to detect physiological and metabolic problems in the crop. This information is then cross-referenced with historical climate data and production targets to indicate to the producer the potential problems their crop will encounter during the production cycle. These problems are prioritized to provide an action plan to address them, thereby balancing all the variables involved in plant growth and drastically reducing the use of fertilizers and agrochemicals.

[0017] BRIEF DESCRIPTION OF THE FIGURES

[0018] The characteristic details of this novel preventive, predictive, and prescriptive analysis process for precision agriculture are clearly shown in the following description and accompanying figures, as well as an illustration thereof, using the same reference symbols to indicate the parts shown. However, these figures are shown by way of example and should not be considered limiting to the present invention. Figure 1 shows the system for implementing the process.

[0019] Figure 2 shows the steps of the first stage of the process for obtaining the Productive Capacity index.

[0020] DETAILED DESCRIPTION OF THE INVENTION

[0021] For a better understanding of the present invention, the parts that make up the system for the preventive, predictive and prescriptive analysis process for precision agriculture of the present invention are listed below:

[0022] 100. Agronomic Intelligence Engine.

[0023] 102. Mobile device.

[0024] 104. Platform.

[0025] 106. Measuring station.

[0026] 108. User.

[0027] 110. Network.

[0028] 112. External data server.

[0029] 114. Communication layer.

[0030] 116. Database.

[0031] In one implementation, a preventive, predictive and prescriptive analysis process is developed with a new generation of ADSS (Agricultural Decision Support Systems) that evolves from data monitoring to personalized and specific recommendations of agricultural inputs to achieve the performance, quality, profitability and sustainability objectives of the agricultural production unit.

[0032] The invention uses an agronomic algorithm called the Agronomic Intelligence Engine (100), which uses emerging technologies such as: Internet of Things, big data, machine learning, artificial intelligence and digital media to have measurement points (input data), and visualization, display and analysis of correlations between variables (process), to generate general and specific recommendations for agronomic management (process output data), which allows the farmer to promote preventive and regenerative agriculture that solves the problems of pollution, health, productivity and profitability caused to date by inadequate crop management.

[0033] The Agronomic Intelligence Engine (100) combines data from the Plant, Water, Soil and Weather Factors (historical, present and forecast) with the purpose of increasingly understanding the functioning of nature in the interaction of these Factors; this system will allow promoting the location of crops in the most favorable environmental conditions to their requirements in order to progressively avoid stress conditions and consequently obtain greater yield and quality of products.

[0034] The data is grouped in the Agronomic Intelligence Engine, in seven sections, plus the general data of the production unit to be served; the sections are:

[0035] 1. Phenology.

[0036] 2. Fertility.

[0037] 3. Nutrition.

[0038] 4. Irrigation.

[0039] 5. Pests.

[0040] 6. Diseases.

[0041] 7. Interaction of Factors.

[0042] The data are classified into indices and elements, and come from laboratories, on-site sensors, weather stations, telemetry (satellite, drones), and our own calculations. The total number of indices per section is as follows: Phenology = 25;

[0043] Fertility=78 : includes Plant=ll, Water=20, Soil=34, Biological=13.

[0044] The elements included for Atmospheric Weather are 6, which are broken down into 64 for agronomic interpretation according to the requirements of the crop.

[0045] For Plant, Water and Soil, 41 chemical elements are included, classified as: Essential=1 6, Beneficial=07, Toxic=15 and Carbon, Hydrogen and Oxygen.

[0046] The data from these indices and elements are used by the Agronomic Intelligence Engine (100), in the sections of Phenology, Fertility, Nutrition, Irrigation, Pests, Diseases and Interaction of Factors.

[0047] The Agronomic Intelligence Engine (100) has two outputs:

[0048] 1. Static Preventive Productive Capacity Index.

[0049] 2. Regenerative Dynamic Productive Capacity Index.

[0050] The first stage of the method is obtaining the Static Preventive Productive Capacity Index. The care model begins with what is called the Static Preventive Productive Capacity Index; this index is determined by comparing the requirements of different crops, varieties, hybrids, and / or biotypes in general with the data corresponding to the location where they are found.

[0051] The crop requirements are rated on 5 levels (very high, high, optimal, low, and very low). A restriction factor is established for each level based on the data. The optimal level is 1, and the restriction factor applied depends on the level at which the data falls.

[0052] Additionally, a weighting factor is estimated for each of the indices and with it the weighted productive capacity index is determined, thus providing the percentage of the "Agronomic Accounting".

[0053] That is, atmospheric "ties" are detected; soil (physical, chemical), water and biological; it is also possible to include information on the composition of the plant and / or fruits obtained in the evaluated production unit.

[0054] The Static Preventive Productive Capacity Index also allows for the identification of the baseline for carbon credit projects, as well as the identification of the "agronomic risk" factor that may affect the financial sector and insurance companies involved with the agricultural production unit. For any investor in an agricultural production unit, the Static Preventive Productive Capacity Index should be part of their agronomic due diligence.

[0055] Once the "constraints" that limit the genetic potential of the crop and the fertility of the agricultural production unit have been identified, the actions to be taken to correct and improve the productive capacity are determined, including personalized and specific recommendations of the agricultural inputs that will be needed to release the constraints that limit the genetic potential of the crop and the fertility of the agricultural production unit.

[0056] In extreme cases, the recommendations may even include changing crops. If this occurs, the system generates recommendations for alternative crops, taking into account the conditions of the agricultural production unit using an efficiency model that considers: agronomic, commercial, and operational feasibility, estimated transition costs, and expected returns per crop.

[0057] The Static Preventive Productive Capacity index is calculated using general average crop requirements, since currently, in general, accurate data on the requirements corresponding to the phenological stages are not available.

[0058] The first output of the Agronomic Intelligence Engine (100) is performed using the following steps:

[0059] Step 1. Obtain (10) the customer record with the following data:

[0060] • Customer name (Individual or Legal Entity)

[0061] • Geographic location of the property (coordinates)

[0062] • Number of hectares of the property

[0063] • Type of crop (Established or to be established)

[0064] • Production target (In tons per hectare).

[0065] The geographic location of the property can be obtained in two ways: a. On-site visit: the technician records the coordinates of the property using a mobile device (102), which can be a cell phone or a GPS device, and then provides them as input into the system. b. Remotely: the technician locates the property on the map, places a PIN on it, and the corresponding coordinates are obtained through an API.

[0066] Step 2. Upload (20) of the pdf files to a web server platform (104) for receiving analysis results, from any laboratory, of the physical, chemical and biological characteristics of the following elements of the property, soil, water and plant.

[0067] Step 3. Capture (30) of the analysis results which is done by means of an Artificial Intelligence text reader, which scans the received pdfs and extracts the results to the database in which they are grouped and stored.

[0068] Using an artificial intelligence engine that identifies and extracts "tokens" within a PDF document or image, this technique is employed to analyze soil, water, plant, and microbiological data from any laboratory. The extraction of this data generates a data sheet file that serves as a guide for interpreting the extracted tokens and relating them to the elements of interest. This guide enables the analysis of any laboratory study, regardless of the laboratory that conducted it.

[0069] Step 4. Process (40) Using the Agronomic Intelligence Engine (100), the process of correlating the information between the analyses uploaded to the platform is carried out, adding to said analysis according to the geographical coordinate of the property (captured by the client in step 1 (10)), the climatic data of the area by means of a measuring station (106) to complete the total information required.

[0070] Historical climate data for the area can be obtained in two different ways: a. Through a measuring station (106) located on the property itself, which has sensors for temperature, humidity, wind speed, and solar radiation that transmit data every 15 minutes via GSM. b. Through an external data server (112) from a global climate provider that provides the same values ​​mentioned in the previous section for the given date and time, given the property's geographic coordinates.

[0071] Step 5. Issue (50) a rating on the feasibility of developing an agricultural project, using the Agronomic Intelligence Engine (100) which has weighting factors, with a reliability index that depends on the number of factors entered.

[0072] The ratings are determined in accordance with best agronomic practices, which serve to establish rating ranges (very high, high, normal, low and very low) for each element measured in the different categories to be evaluated (plant, water, soil, weather, microbiology) and considering the particular crop being analyzed.

[0073] These best practices allow us to determine if, for example, the level of Nitrogen in the soil is suitable for the crop being analyzed, and it is established that if the value is higher than n parts per million (ppm) then it falls into the very high range, if it is between n-2 and n-1 ppm then it falls into the high range and so on until the very low range.

[0074] Each range is assigned, in accordance with best agronomic practices, a restriction factor and each evaluated element is associated with a weighting factor.

[0075] The weighting factor gives greater weight to elements that are more important compared to others. For example, in physical soil fertility indices, a higher weighting factor is given to Available Moisture (%), Organic Matter (%), and Soil Penetration Resistance (MPa).

[0076] Step 6. Report (60) deficiencies and / or constraints of soil, water and / or climatic conditions using the Agronomic Intelligence Engine (100) reports.

[0077] Step 7. Correlate (70) using the Agronomic Intelligence Engine (100) correlates the information on the type of crop and the production objective (captured by the client in step 1) to issue the opinion in step 8 (80).

[0078] Step 8. Issue (80) using the Agronomic Intelligence Engine (100) a document with agronomic management recommendations for improvements, amendments, or adjustments to the physical and chemical characteristics of soil and water elements, in order to increase the rating of said project. The system can generate recommendations for alternative crop changes, taking into account the conditions of the agricultural production unit with an efficiency model that considers: agronomic, commercial, and operational feasibility, estimated transition cost, and expected returns per crop.

[0079] Step 9. Establish (90) using the Agronomic Intelligence Engine (100) a general static agronomic management plan of nutrition needs, fertility, irrigation and pest and disease control stages according to the processed information, to achieve the goals according to the required production objective.

[0080] The process performs a comprehensive analysis of the soil where the crop is located and compares it against the conditions that the plant needs to achieve the desired production goal, delivering to the producer a production plan focused on producing more with fewer chemically synthesized inputs.

[0081] The results of this information are used to obtain the second output of the Agronomic Intelligence Engine (100), and to propose a tailor-made plan called "Regenerative Dynamic Productive Capacity Index".

[0082] This index reports in real time the weather conditions and the availability in the soil of water and nutrients for the development and growth of the crop against its requirements; based on this information, the most appropriate management is determined by Phenological Stage for the production and quality of the harvest.

[0083] In addition to the indices used for the Regenerative Dynamic Productive Capacity index, meteorological and soil information, especially temperature, humidity and heat units, is also used to determine the best management of pests and diseases.

[0084] The substantive part for a crop to express its yield potential and harvest quality, besides the weather, is the available water and nutrients, therefore the platform (104) includes the 41 chemical elements presented in the data sheet called Elements, which apply to Plant, Water and Soil.

[0085] The dataset that the system captures, processes, correlates, and interprets is more extensive than what is typically used in traditional agricultural management. This is essential for understanding how nature functions in the interaction between plants, water, soil, and weather. It requires having access to all current data and any additional data added through scientific discoveries. In this second stage, based on the Static Preventive Productive Capacity Index, a data feed dynamic is developed. Data is continuously captured on the property via the measurement station (106) installed there, updating the indices and elements that the Static Preventive Productive Capacity Index considers for the ongoing evaluation of the project. This allows for the issuance and implementation of amendments and / or corrections to the soil, irrigation, and / or plants.

[0086] Through the Regenerative Dynamic Productive Capacity Index, several models and / or plans can be determined, such as:

[0087] Nutritional Management Plan. Through constant monitoring of the climate and soil, and correlation with the physical-chemical analyses of soil and water, of the Static Preventive Productive Capacity index, a model of nutrition and soil conditioning is determined sufficient in milligrams per liter (mg / 1) instead of kilograms per hectare (kg / ha) to achieve a balance between soil regeneration and the needs of the plant.

[0088] Agronomic Fertility Plan. Through constant climate monitoring and correlation with plant analyses, indices are determined that influence the plant's phenological stage changes, thus enabling recommendations on the plant's stress status and possible solutions to guide the plant through its phenological stages in the best possible way.

[0089] Agronomic Irrigation Management Plan. Through constant monitoring of the climate, soil, and correlation with the physical analyses of the soil and water of the Static Preventive Productive Capacity Index, the behavior of the laminar flow of water and its availability to the plant is determined, allowing adjustments to be made in the irrigation plans so that a balance is developed that allows the renewal of the soil and also has sufficient moisture for the plant without degrading it.

[0090] Agronomic Plan for Pests and Diseases. Through constant monitoring of the climate on site, the correlation of its variables and the algorithms of risk of appearance of pests and diseases in their different states and / or thresholds, the best time to control their appearance is determined by changing from a reactive application to a preventive one.

[0091] By correlating all the elements and indices reflected in the four management plans, weighting factors are used to identify the elements that require the highest priority and that have the greatest impact on soil and plant health. The aim is always to maintain a balance between the various physical and chemical elements of the soil, water, and plants, to avoid antagonisms or blockages between them.

[0092] Finally, an analysis is carried out between the recommendations and the agricultural practices that are carried out to determine the correct balance between these and thus generate a balance between the viability of the agricultural project, its practices, the inputs to be used and the business plan.

[0093] The Agronomic Intelligence Engine (100) continues to generate personalized and specific recommendations for agricultural inputs, as well as intelligent, corrective, and preventive recommendations for agronomic management in six critical areas for any farmer: Phenology, Fertility, Nutrition, Irrigation, Pests, and Diseases.

[0094] Personalized and specific recommendations for agricultural inputs take into account technical factors, such as the identification in the formulation of the agricultural input of physical, chemical and biological elements that could be antagonistic, as well as the cost-benefit factor, and geographical availability of the agricultural input.

[0095] The process is implemented in a system that is configured to perform the previously described process methodologies, showing a field environment with other devices with which the system can interoperate.

[0096] In one embodiment, a user (108) owns or operates a mobile device (102) at a property location such as a field used for agricultural activities. The mobile device (102) is configured to provide property information to a web server platform (104) via one or more networks (110). The platform (104) is configured with the Agronomic Intelligence Engine (100) to receive input data from the mobile device (102), receive data from a measuring station (106), and receive input data via an external data server (112), and then send output data to the mobile device (102) via the network (110). It also comprises a database (116) for storing the information received on the platform (104).

[0097] The platform (104) is configured to operate with the Agronomic Intelligence Engine (100), for the reception of input data, through the mobile device (100), the measuring station (106) and the external data server (112); so that the platform (104) processes the data and generates the two types of output, the Static Preventive Productive Capacity Index and the Dynamic Regenerative Productive Capacity Index, in order to generate personalized and specific recommendations.

[0098] In one embodiment of the invention, the data acquired by the measuring station (106) can be through an external data server (112) that includes historical meteorological data for the provided date-time, given the geographical coordinates of the property.

[0099] The measuring station (106) may have one or more remote sensors attached to it, including environmental and soil sensors that are communicatively coupled, transmitting every 15 minutes, either directly or indirectly via the network (110). These environmental sensors may measure temperature, CO2, humidity, wind speed, rainfall, and solar radiation. The soil sensors may measure electrical conductivity, temperature, humidity, pH, and nutrients (phosphorus, nitrogen, potassium).

[0100] The network (110) can be any combination of one or more data communication networks, including local area networks, wide area networks, internetworks or the internet, using any wired or wireless links, including terrestrial or satellite links.

[0101] A communication layer (114) configured to perform input / output interface functions, including sending requests to the mobile device (102), the platform (104) and the measuring station (106) respectively.

[0102] The use of this system fosters a shift from reactive and emergency agriculture to preventive and regenerative agriculture. Essentially, it aims to induce a change in the attitude of those involved in agricultural activity, shifting the priority of action from individualism to teamwork, communicating to accelerate the understanding of how nature functions in the Plant, Water, Soil, and Weather (PASTA) interaction, thus changing the priority of action.

[0103] A. Data before input. Shifting the focus from "what I add" to "why I add it" or "why I don't add it." B. Agronomic accounting before economic accounting. Assessing available natural resources (installed capacity) and deciding how to use the land.

[0104] C. Collective research before individual research. Interdisciplinary teams (Producers, technicians, scientists, academics, suppliers, public servants, providers).

[0105] D. Field research before laboratory research. Investigate the best crop management practices to produce without harming the environment, not just the best input to sell to the farmer.

[0106] In view of what has been set out in this descriptive chapter, it is reiterated that the scope of the present invention should not be limited by the modalities particularly described, and it is understood that variations may be made in several ways.

[0107] These variations should not be considered as a departure from the spirit and scope of the invention, and all such modifications may be obvious to a person skilled in the art and should be included within the scope of the following claims.

Claims

CLAIMS 1. A preventive, predictive and prescriptive analysis process for generating static preventive and dynamic regenerative productive capacity indices for precision agriculture, implemented on a web server platform (104) configured with an Agronomic Intelligence Engine (100), characterized in that it comprises: A first stage implemented in an Agronomic Intelligence Engine (100) to obtain the Static Productive Capacity index, through the steps of Obtain (10) the customer record by means of a mobile device (102) of the user (108) connected to the network (110); Upload (20) the pdf files to the web server platform (104) for receiving laboratory analysis results, of the physical, chemical and biological characteristics of the following elements of the property, soil, water and plant; Capture (30) the results of the analyses using an artificial intelligence text reader included in the Agronomic Intelligence Engine (100) that extracts the results to the database (116) in which they are grouped and stored; Process (40) by means of the Agronomic Intelligence Engine (100) the correlation of the information between the analyses loaded on the platform, adding to said analysis according to the geographical coordinate of the property, the climatic data of the area by means of a measuring station (106) placed on the property that has sensors of temperature, humidity, wind speed and solar radiation; Issue (50) a rating on the feasibility of developing an agricultural project, using the Agronomic Intelligence Engine (100) which has factors of weighting with a reliability index that depends on the number of factors entered; Report (60) deficiencies and / or constraints of soil, water, biology and / or climatic conditions using the Agronomic Intelligence Engine (100); Correlate (70) using the Agronomic Intelligence Engine (100) the information on the type of crop and the production objective; Issue (80) through the Agronomic Intelligence Engine (100) a document with automatic management recommendations for improvements, amendments or adjustments to the physical and chemical characteristics of soil and water elements in order to increase the project's rating; Establish (90) through the Agronomic Intelligence Engine (100) a general static agronomic management plan of nutrition needs, fertility, irrigation and pest and disease control stages according to the processed information, to achieve the goals according to the required production objective; A second stage implemented in the Agronomic Intelligence Engine (100) to obtain the Regenerative Dynamic Productive Capacity index, in addition to incorporating the results of the first stage; reports in real time the weather conditions and the availability in the soil of water and nutrients for the development and growth of the crop against its requirements; Determine, using the Agronomic Intelligence Engine (100) based on the information obtained, the appropriate management for the phenological stage for the production and quality of the harvest; Determine, using the Agronomic Intelligence Engine (100) based on meteorological and soil information, such as temperature, humidity and heat units, the best management of pests and diseases; Develop, through the Agronomic Intelligence Engine (100), a dynamic system for feeding data captured permanently on the property through the measuring station (106) installed on the property, updating the indices and elements that the Static Preventive Productive Capacity index considers for the constant evaluation of the project; and, Issue and make amendments and / or corrections using the Agronomic Intelligence Engine of the soil, irrigation and / or plant.

2. The predictive and preventive analysis process, in accordance with claim 1, further characterized in that: in the Establish step (90) of the first stage, in extreme cases, the recommendations may even include changing the crop; if so, the system generates recommendations for alternative crop changes, taking into account the conditions where the agricultural production unit is located, with an efficiency model that considers: agronomic, commercial and operational feasibility, estimated transition cost, and expected returns per crop.

3. The predictive and prescriptive analysis process according to claim 1, further characterized in that: the Regenerative Static Productive Capacity index is determined by comparing the requirements of the different crops, varieties, hybrids and / or biotypes in general with the data corresponding to the place where it is located.

4. The predictive and prescriptive analysis process according to claim 3, further characterized in that: the crop requirements are classified into 5 levels, very high, high, optimal, low and very low.

5. The predictive and prescriptive analysis process according to claim 1, further characterized in that: a weighting factor is estimated for each of the indices and with it the weighted productive capacity index is determined.

6. The predictive and prescriptive analysis process according to claim 1, further characterized in that: the user record includes the client's name, geographical location of the property, number of hectares of the property, type of crop or production objective.

7. The predictive and prescriptive analysis process according to claim 6, further characterized in that: the geographical location of the property can also be obtained remotely by placing a PIN through an API to obtain the corresponding coordinates.

8. The predictive and prescriptive analysis process according to claim 1, further characterized in that: the step of capturing the results of the analyses using an artificial intelligence text reader allows the identification of tokens in a pdf document or image to read the analyses of soil, water, plant, microbiology from any laboratory.

9. The predictive and prescriptive analysis process according to claim 8, further characterized in that: through the extraction of this data, a data sheet file is constructed which serves as a guide to interpret the tokens extracted from the document and relate them to the elements of interest for analysis.

10. The predictive and prescriptive analysis process according to claim 1, further characterized in that: the climate data can also be obtained by means of an external data server (112) from a global climate provider that provides the same values ​​mentioned for the provided date-time, given the geographical coordinates of the property.

11. The predictive and prescriptive analysis process according to claim 1, further characterized in that: The ratings are determined in accordance with the best agronomic practices that serve to establish rating ranges for each element measured in the different categories to be evaluated and considering the particular crop being analyzed.

12. The predictive and prescriptive analysis process according to claim 1, further characterized in that: by constantly monitoring the climate and soil and correlating it with the physical, chemical and biological analyses of soil and water of the Regenerative Dynamic Productive Capacity index through the Agronomic Intelligence Engine, a soil nutrition and conditioning model is determined that is sufficient in milligrams per liter (mg / 1) to achieve a balance between soil regeneration and plant needs.

13. The predictive and prescriptive analysis process according to claim 1, further characterized in that: by constantly monitoring the climate and correlating it with plant analyses through the Agronomic Intelligence Engine (100), indices are determined that influence the plant for its phenological stage changes, thus being able to issue recommendations on the stress state in the plant and its possible solutions to take the plant in the best way through its phenological stages.

14. The predictive and prescriptive analysis process according to claim 1, further characterized in that: through constant monitoring of the climate, soil and correlation with the physical analyses of the soil and water of the Regenerative Dynamic Productive Capacity index, through the Agronomic Intelligence Engine (100), the behavior of the laminar flow of water and its availability to the plant is determined, allowing adjustments to be made in the irrigation plans so that a balance is developed that allows the renewal of the soil and It also provides sufficient moisture for the plant without degrading it.

15. The predictive and prescriptive analysis process according to claim 1, further characterized in that: by constantly monitoring the climate on site, correlating its variables and the irrigation algorithms, the appearance of pests and diseases in their different states and / or thresholds through the Agronomic Intelligence Engine (100), the best time to control their appearance is determined by changing from a reactive application to a preventive one.

16. A system for the predictive and prescriptive analysis process for generating static preventive and dynamic regenerative productive capacity indices, characterized in that it comprises: A user's mobile device (102) (108) configured to provide property information to a web server platform (104) via a network (110); A measuring station (106) having one or more fixed remote sensors communicatively coupled via the network (110) to send data to the platform (104); An external data server (112) that includes historical meteorological data connected to the platform (104) via the network (110); A network (110) having a communication layer (114) configured to perform data input / output interface functions to the mobile device (102), the platform (104) and the measuring station (106); and, A web server platform (104) comprising a database (116) for storing information received by the mobile device (102), the measuring station (106) and the external data server (112) via the network (110) and an Agronomic Intelligence Engine (100) configured to carry out the process according to claims 1 to 14.

17. The system according to claim 16, further characterized in that: the sensors of the measuring station (106) can be ambient and soil sensors that are communicatively coupled, transmitting every 15 minutes, either directly or indirectly through the network (110).

18. The system according to claim 17, further characterized in that: the environmental sensors can be for temperature, CO2, humidity, wind speed, rainfall and solar radiation and the soil sensors can be for electrical conductivity, temperature, humidity, pH, nutrition (phosphorus, nitrogen, potassium).

Images