123 results about "Soil conductivity" patented technology

The invention discloses an intelligent water and fertilizer integrated precise irrigation control method. The method comprises the following steps: step 1, establishing a multi-modal data acquisition network; step 2, inputting the data obtained in the step 1 into a trained LSTM neural network, and predicting future crop transpiration water demand; 3, according to nutrient concentration distribution fed back by a soil conductivity sensor in real time, combining with a water and fertilizer coupling migration model, dynamically calculating a nitrogen-phosphorus-potassium ratio of each irrigation zone, realizing precise mixing of a fertilizer mother solution and irrigation water through a three-channel proportioning pump, and implementing a variable irrigation decision; 4, dynamically adjusting the pulse irrigation duration of each branch through an MPC algorithm; and step 5, recovering the residual liquid at the tail end of the pipe network to a buffer tank, detecting the EC value of the recovered liquid through an electrochemical sensor, and taking the EC value as a reference parameter automatic correction proportioning algorithm of the next irrigation period. Accurate control over the irrigation process can be achieved, so that the water and fertilizer utilization efficiency is improved, and resource waste and environmental pollution are reduced.

The invention discloses a method and system for estimating irrigation water consumption and water utilization efficiency, and relates to the technical field of water resource management, and the method comprises the steps: collecting the plant stem flow rate, canopy temperature and soil profile water content data of a target area through a multi-source sensing device, and obtaining a gradient and permeability distribution diagram of a geographic information system; dividing the farmland of the target area into sub-areas with different irrigation priorities based on a soil conductivity mutation point detection algorithm; constructing a dynamic water demand model fused with the plant transpiration hysteresis effect, performing space-time correlation analysis on the stem flow rate data and the soil moisture content gradient, and calculating the real-time water demand intensity of each sub-region; the method comprises the following steps: accessing short-time rainfall prediction data of a meteorological radar, dynamically correcting a future irrigation decision by adopting a sliding time window mechanism, and triggering a gradient delay irrigation instruction when the predicted rainfall amount exceeds an irrigation threshold value; and calculating the actual moisture utilization efficiency based on the inversion data of the moisture content of the irrigated soil and the unmanned aerial vehicle multispectral image.

The invention discloses a soil salinity inversion method, system and device based on multi-mode remote sensing data fusion and a storage medium, and is applied to the technical field of soil quality monitoring, and the method comprises the steps: obtaining radar and optical remote sensing data of a to-be-inverted region of soil salinity, and carrying out the conductivity measurement, and taking the obtained data as an inversion index of the soil salinity; obtaining multi-modal remote sensing features based on radar and optical remote sensing data fusion, optimizing a remote sensing feature combination by combining the radar and optical remote sensing data and based on a random forest algorithm and utilizing a recursive feature elimination method, and performing model performance evaluation on the remote sensing feature combination by adopting cross validation to obtain an optimal remote sensing feature combination; and based on the optimal remote sensing feature combination, constructing and training a soil conductivity prediction model based on a random forest algorithm, and inputting to-be-measured data to the conductivity prediction model after hyper-parameter adjustment to complete soil salinity inversion. According to the method, more accurate inversion of the soil salinity under the interaction influence of a complex environment and human factors is realized.

The invention relates to the technical field of crop saline-alkaline tolerance analysis, in particular to a rice saline-alkaline tolerance prediction method and system based on big data analysis, and the method comprises the following steps: collecting soil environment data, rice physiological phenotype data and historical stress response data, and constructing a multi-dimensional data cube by using a space-time alignment engine; quantization feature analysis is adopted to carry out quantum probability modeling on Na < + > / K < + > ion transmembrane transport and PSII photosynthetic exciton transfer features, and a quantum probability cloud chart of rice physiological response is generated. Based on a geodesic line domain adaptation model of geodesic line mapping, a soil conductivity thermodynamic diagram and a quantum probability cloud chart are fused, a rice saline-alkaline tolerance adaptability prediction model is established, finally, a three-dimensional saline-alkaline tolerance performance prediction map is output, and the adaptability of rice varieties in specific saline-alkaline land is visually displayed. According to the method, the regional generalization ability of saline-alkali tolerant varieties is effectively improved, the limitation of a traditional statistical model is broken through, and a scientific basis is provided for saline-alkali tolerant rice breeding and cultivation and saline-alkali soil agricultural optimization management.

The invention relates to the technical field of termite monitoring and killing, in particular to a termite monitoring and killing method based on multi-modal sensing and a dynamic threshold value, and adopts the technical scheme that multi-source signal acquisition is adopted, and biological activity signals of a target area are synchronously acquired through a vibration sensor, a sonic sensor, a chemical gas sensor and a thermal imaging sensor; the anti-interference performance is improved, so that the false alarm rate is reduced; environmental parameter compensation is carried out, temperature, humidity and soil conductivity data are collected in real time, a dynamic calibration coefficient is generated to correct sensor original data, and environmental adaptability is improved; the method comprises the following steps: acquiring data of a current area, performing dynamic threshold calculation, inputting the acquired data into an LSTM-Transformer hybrid network, and outputting a self-adaptive early warning threshold of the current area so as to reduce the possibility of leak detection; through multi-stage early warning judgment, the real-time performance is improved, and the early warning delay is reduced; and starting a corresponding disposal process according to the early warning level, performing response execution, and narrowing the spraying range, thereby reducing pollution.

The invention relates to the technical field of intelligent control, and discloses a water-saving fertilization variable control method suitable for sandy soil, and the method comprises the steps: obtaining collection data based on a sensor; and establishing and updating an infiltration-storage-leaching loss prediction model of the sandy soil according to the collected data, performing state estimation on soil moisture and nutrient states, and calculating root layer moisture deviation, fertilizer concentration deviation and deep seepage risk. And executing model predictive control in the rolling time domain to obtain a control result. And executing water-saving fertilization operation according to the control result. In the execution process, the soil volume moisture content, the soil water potential, the soil conductivity and shallow layer leakage observation data are fused, the prediction model is corrected, the control result is dynamically adjusted according to the correction result, and when the environment wind speed exceeds a set threshold value, the spray irrigation parameters are corrected. The fine level of control is improved, deep layer leakage can be inhibited under the sandy soil condition, water and fertilizer balance of a root layer is guaranteed, and external disturbance is coped with.

The invention provides a rice growth model construction method and system based on salt stress, and relates to the technical field of growth model.The rice growth model construction method comprises the steps that firstly, monitoring points are arranged in a planting sample area, and soil conductivity data of different depths are obtained through a multi-depth soil conductivity sensor and a Kriging interpolation method; collecting root system density, a multispectral remote sensing image and a leaf area index, and calculating a canopy salt stress index; measuring the concentration of related ions to obtain a sodium adsorption ratio, and establishing a salt stress coefficient by combining the soil conductivity and the irrigation volume; fusing canopy and soil stress indexes to generate a stress comprehensive index, and introducing a salinity feedback item to represent the crop compensation capability; and finally, constructing a hybrid machine learning model by adopting a convolutional neural network and a long-short-term memory network to realize rice growth dynamic prediction. According to the method, multi-dimensional salinity stress quantification of a soil-crop system is realized, and decision support is provided for salinization treatment in precision agriculture.

The invention discloses a DNAPLs pollutant diffusion migration path depicting method and system, and relates to the technical field of pollution monitoring, and the method comprises the steps: obtaining the soil conductivity of a target region through an improved TDR probe, obtaining the time sequence characteristics and spatial characteristics of a soil conductivity data set, obtaining the fusion spatial-temporal characteristics, calculating the spatial-temporal similarity of historical migration paths, and obtaining the DNAPLs pollutant diffusion migration path depicting result. Screening prior knowledge; constructing a space-time prediction model by using a graph neural network and priori knowledge, extracting deep space-time features from a space adjacent graph and a time-dependent heterogeneous graph corresponding to the target region, and obtaining a conductivity prediction value of a future time step; the diffusion direction of the pollutants is deduced by combining the relation between the resistivity and the DNAPLs concentration, migration frontal surface diagrams at different time points are drawn, and dynamic path visualization is achieved. According to the method, the improved TDR (time domain reflectometry) technology and the deep learning model are combined, so that high-precision monitoring and prediction of the dynamic migration process of the pollutants are realized.

The invention relates to the technical field of environment monitoring, in particular to an intelligent digital rural environment monitoring system and method based on big data, and the system comprises a layered water potential collection module, a gradient reverse correction module, a path inversion modeling module and a multi-dimensional diffusion modeling module, and the layered water potential collection module calculates and generates rural soil environment monitoring data; the rural soil environment monitoring data comprises layered soil water potential distribution, soil water content gradient and a soil conductivity characteristic value, and the soil water potential abnormal flow data comprises a vertical water potential difference value, an abnormal water flow direction vector and a water flow intensity grade; the moisture permeation path distribution diagram comprises a permeation path distribution structure, a soil water potential accumulation interval and a water flow propagation direction identifier, and the diffusion boundary space model comprises a pollutant diffusion boundary range, a moisture transverse migration region and multi-dimensional diffusion rate distribution. According to the scheme, the abnormal distribution range, the duration time and the development trend are quantitatively described, and the research and judgment accuracy of the abnormal penetration and diffusion process is improved.

The invention provides a photovoltaic system and power distribution network state cooperative monitoring method based on the Internet of Things, and the method comprises the steps: deploying a multi-point collection device in a key region of a photovoltaic power station through a sensor network, and obtaining the soil humidity change and soil conductivity at regular time; denoising and standardizing the acquired soil humidity change and soil conductivity data to generate a standardized environmental parameter matrix; according to the dynamic change trend of grounding grid corrosion, identifying the mapping relation between the soil environment parameters and the grounding resistance value, and combining the real-time environment parameters and the corrosion trend to predict the resistance change; and comparing the predicted resistance change with the current grounding resistance value in real time, if the current grounding resistance value is detected to exceed a safety threshold range, triggering an abnormal early warning signal, and determining a potential area with high electric shock risk according to the resistance deviation degree and the corrosion rate.

The utility model relates to the technical field of soil in-situ detection, and discloses a portable soil quality multi-parameter in-situ detection device. The device mainly comprises a controller, a connecting wire, an optical probe and a sensor. The controller is provided with a touch screen, a single-chip microcomputer circuit board, a single-chip microcomputer, an SD card, a key switch, a wireless communication control panel and a power source, and power source management, detection system control, real-time data processing, man-machine interaction, data storage and remote transmission can be achieved. The sensor comprises a soil temperature probe, a soil humidity probe, a soil conductivity probe and a soil pH probe, and can realize real-time data acquisition of soil temperature and humidity, conductivity and pH value; an annular lamp holder, a light source, a photoelectric sensor, a plano-convex lens, a light shielding plate, a light shielding boss and a light shielding ring are arranged in the optical probe, and rapid collection of soil organic matter spectrum information can be achieved. The soil in-situ detection device realizes synchronous acquisition of multiple parameters of soil, is reasonable in structural design and convenient to operate, and is suitable for popularization and application in the field of soil in-situ detection.

The invention relates to an unbalanced data-oriented electric power system lightning disaster risk detection method, which comprises the following steps of: S1, gridding a target detection land parcel to obtain a plurality of grid units; S2, based on latitude and longitude coordinates of each grid unit, obtaining line parameters and environment characteristics of each grid unit in combination with a line database and a geographic information base, wherein the line parameters comprise tower height, span, grounding resistance, loop number, lightning arrester number and transformer capacity, and the environment characteristics comprise soil conductivity, building height and land utilization type; and S3, inputting the line parameters and the environment characteristics of each grid unit into a trained first detection model to obtain the thunder and lightning probability and the maximum peak current of each grid unit. Compared with the prior art, the multi-source data such as the tower height, the span, the grounding resistance and the soil conductivity are comprehensively considered, and the risk assessment result has higher regional adaptability and accuracy.

A power transmission tower grounding resistance non-contact measurement method based on the electromagnetic coupling principle comprises the following steps that transmitting and receiving electromagnetic coupling coils are arranged around an iron tower grounding body, and geometric calibration and spatial positioning of a measurement area are completed by combining grounding grid structure parameters and soil conduction characteristics; injecting a high-frequency alternating-current excitation signal into the transmitting coil, and synchronously acquiring the amplitude and phase response of the induced voltage at a receiving coil end; carrying out filtering processing on the induction signal by adopting a time-frequency analysis and phase decoupling algorithm, and solving a function relationship between electromagnetic response and grounding impedance by combining a coupling equivalent model; based on experimental calibration data and scene parameters, a nonlinear mapping model of induction response and grounding resistance is constructed, and real-time inversion calculation is carried out by combining a solving result obtained in the third step. According to the invention, the real-time accurate measurement of the grounding resistance under the conditions of no power failure and no wire breakage is realized, and the safety, the operation convenience and the anti-interference capability in a complex environment in the measurement process are obviously improved.

The invention discloses a salinization remote sensing inversion method fusing crop information and data preprocessing. A land utilization data set is subjected to splicing, cutting and other processing to obtain a high-confidence-coefficient cultivated land range; point distribution sampling is carried out according to a regular grid method, and soil conductivity is measured; preprocessing the remote sensing image; dividing crop growth stages and constructing a multi-temporal spectral feature set; constructing an NDVI time sequence data set and extracting phenological characteristics; extracting planting structure information based on the multi-temporal spectrum and phenological characteristics; a planting structure is converted into crop type data through one-hot coding, and the crop type data is fused with multi-temporal spectrum and phenological characteristics to construct a crop information data set; the method comprises the following steps: constructing a salinity inversion model through data preprocessing and combining with ground actually measured salinity data, and verifying the salinity inversion model; evaluating the cross-year generalization ability of the model; and finally, the inversion result is visualized to generate a salinization map. According to the invention, the system integrates the multi-dimensional information of crops and optimizes the data preprocessing process, and significantly improves the salinization monitoring precision and the cross-space-time adaptability.

The invention relates to a composite microbial inoculant for soil improvement, the composite microbial inoculant for soil improvement is composed of PGPR (Pseudomonas tianjinensis) and AMF (Amplified Macrophage Fungi), the PGPR is Pseudomonas tianjinensis and Pseudomonas oryzae, and the AMF is rhizophagus clarus. The composite microbial inoculant for soil improvement is characterized in that the PGPR is Pseudomonas tianjinensis and Pseudomonas oryzae, and the AMF is Pseudomonas oryzae, the PGPR is Pseudomonas tianjinensis and Pseudomonas oryzae. According to the invention, the Pseudomonas tianjinensis, Pseudomonas oryzae and AMF are compounded, so that a synergistic effect is exerted, an obvious growth promoting effect on the ryegrass in the saline-alkali soil is achieved, the content of photosynthetic pigments in the ryegrass is increased, the contents of soluble sugar, soluble protein, proline and malondialdehyde in the ryegrass are further increased, and the CAT enzyme activity is improved. In addition, the complex microbial inoculant is combined with ryegrass planting, a plant-microorganism synergistic system is formed, salinized soil is effectively improved, the conductivity and pH of the soil are reduced, the content of nitrogen, phosphorus and potassium in the soil and the content of rapidly available phosphorus and rapidly available potassium are increased, and meanwhile the activity of urease and phosphatase is improved.

The invention relates to the technical field of carbon-nitrogen ratio detection, in particular to a sweet potato carbon-nitrogen ratio detection method and system based on a multispectrum and fluorescence sensor, and the method specifically comprises the following steps: constructing a weight coefficient based on the correlation between the leaf carbon-nitrogen ratio in each growth stage and the reflectivity of each wavelength, and combining the multispectrum and fluorescence spectrum of each leaf to obtain a weight coefficient; acquiring a coupling characteristic value; correcting the coupling characteristic value according to the soil conductivity; analyzing the multi-spectral characteristics and the fluorescence spectrum characteristics of the sweet potatoes, and constructing a multi-spectral index and a fluorescence spectrum index; predicting the carbon-nitrogen ratio of the to-be-detected sweet potato leaf based on the features of the leaf, and calculating the carbon-nitrogen ratio of the to-be-detected sweet potato leaf by combining the difference between the feature vectors of the to-be-detected sweet potato leaf and the leaves in all growth stages and introducing the carbon-nitrogen ratio of the previous growth stage; certain continuity and inertia of the change of the carbon-nitrogen ratio are considered, so that the method adapts to the change of the sweet potatoes in different growth stages, and the detection precision of the carbon-nitrogen ratio is improved.

Methods, systems, and computer program products for implementing a soil analysis process. A set of soil data may be received at a device from one or more soil sensors. The one or more soil sensors may be coupled to a portion of an agricultural machine configured to be in contact with soil. The device may be configured to analyze soil when a portion of the one or more soil sensors is in contact with the soil. Spectral data and soil conductivity and / or capacitance data may be obtained based on the collected set of soil data. Analyzed soil data may be determined based on the spectral data and soil conductivity and / or capacitance data. The analyzed soil data may be provided to a user device configured to display a visual representation of at least part of the analyzed soil data.

The invention discloses an irrigation water and fertilizer fine adjustment system and method, and relates to the technical field of agricultural irrigation adjustment, and the method comprises the steps of information collection and storage, visual feature recognition and growth stage matching, irrigation area division, water application amount and fertilization amount calculation, irrigation instruction generation and irrigation operation execution. According to the invention, crop information is collected and visual feature identification is carried out to determine a growth stage, a crop growth stage spatial distribution map is generated, and irrigation area division is carried out according to the map; water and fertility calculation is carried out according to the soil moisture content and the soil conductivity of the soil in the irrigation area to obtain the water application amount and the fertilizer application amount, finally, an irrigation instruction is generated according to the water application amount and the fertilizer application amount, irrigation operation is executed, accurate water and fertilizer supply for crops in different growth stages is achieved, and the irrigation water and fertilizer adjustment fineness is improved.

The embodiment of the invention discloses a soil nutrient classification method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring soil attribute information of a target area within a preset duration; the soil attribute information comprises soil conductivity, soil temperature and spectral reflectivity; performing data preprocessing on the soil attribute information to obtain preprocessed multi-channel time sequence data; performing feature extraction and fusion on the multi-channel time sequence data based on a target feature extraction model to obtain hidden state features; the target feature extraction model is obtained by performing semi-supervised mutual learning on a preset feature extraction model by using different enhanced samples obtained by performing different data enhancement processing on unlabeled samples; and determining a soil nutrient classification result of the target region based on the target classification model and the hidden state features. Through the technical scheme of the embodiment of the invention, the soil nutrients can be accurately and conveniently analyzed, and efficient soil nutrient classification in a few-sample environment is realized.

The invention relates to the technical field of agricultural data visualization, in particular to a salinized cotton field visual multi-point salinity collection and analysis method and system.The method comprises the following steps that soil conductivity distribution data of a salinized cotton field area is obtained, a high-salinity accumulation area and a low-salinity dilution area are recognized, particle gap distribution characteristics are collected, and a salinized cotton field is obtained; and screening areas with loose or compact particle structures, executing temperature gradient analysis, screening surface thermal environment abnormal subareas, detecting wind speed distribution, removing wind field disturbance areas, and obtaining a recommended planting area list. According to the method, high and low salt areas are accurately identified through salt space distribution analysis, distribution precision is improved, humidity dynamic expression is refined, structural abnormal blocks are screened by using a particle gap change trend, soil management is optimized, surface temperature and wind speed data analysis is superposed, thermal disturbance and wind field abnormity are eliminated, and agricultural management precision is improved through multi-dimensional data fusion. The capability of coping with a complex environment is enhanced, efficient decision making is effectively supported, and the overall agricultural production benefit is improved.

The invention belongs to the technical field of agricultural soil conditioners, and particularly relates to a soil conditioner, a preparation method and application. The invention provides a soil conditioner. The soil conditioner comprises fermented sludge, modified bentonite and lignosulfonate, the mass ratio of the fermented sludge to the modified bentonite to the lignosulfonate is (6-8): (2-3): (1-3). When the soil conditioner is applied to saline alkali soil, the pH value of the soil can be reduced, the organic matter content of the soil can be increased, the microbial diversity index (Shannon index) of the soil can be increased, and heavy metal in the soil can be passivated; meanwhile, the soil conductivity value is reduced. Compared with a traditional lime improvement method, the soil conditioner can avoid the risk of secondary alkalization and is good in application effect.

The invention relates to an orchard environment monitoring management system. The system comprises a first acquisition unit used for acquiring soil monitoring data; wherein the soil monitoring data at least comprise soil humidity, soil temperature, soil PH value, soil conductivity and soil tension value; the second acquisition unit is used for acquiring fruit tree growth state information; wherein the fruit tree growth state information comprises growth images of the fruit tree in different growth stages; the third acquisition unit is used for acquiring climate monitoring data; the data processing unit is used for processing the soil monitoring data, the fruit tree growth state information and the climate monitoring data; and the prediction unit is used for predicting the processed soil monitoring data, the fruit tree growth state information and the climate monitoring data through a pre-trained target LSTM network model so as to predict the growth condition of the fruit tree and the orchard environment condition. According to the invention, fruit farmers are helped to make management plans in advance, reasonably arrange manpower and material resources, and realize fine management.

The invention relates to the technical field of tropical agricultural planting, in particular to a method for planting pineapple-high-canopy crops on a steep-slope terrain in a low-latitude region. The planting method comprises the following steps: (1) transforming a terrain and interplanting, namely transforming a contour line terrace along the gradient direction, constructing a stepped planting belt, planting high-canopy crops in terrace ridges, and planting pineapples in the terrace surface; (2) complete-cycle photo-thermal management: the canopies of the high-canopy crops intercept direct light, and the pineapples utilize transmission light or diffused light; (3) water and fertilizer collaborative management: dividing a contour line terrace into multiple stages of irrigation areas according to the elevation difference, configuring an independent drip irrigation pipe network for each stage of irrigation area, monitoring the soil conductivity and the leaf surface transpiration rate in real time, and dynamically adjusting the fertilization amount; slow-release compound fertilizer is applied to high-canopy crops, and the application frequency is 4 times per year; the macroelement water-soluble fertilizer is applied to the pineapples by adopting pulse type drip irrigation, so that the fertilizing period of the pineapples and the fertilizing period of the high-canopy crops are staggered.

A target variable hole depth fertilization device for large-plant-spacing crops in the field, comprising a frame, on which a main control box is installed. A fertilizer box is installed at the rear of the frame. A soil conductivity detection device, a front photoelectric sensor, a furrow opener, a soil covering device and a rear photoelectric sensor are installed at the lower part of the frame. The front photoelectric sensor is arranged directly above the soil conductivity detection device, and the rear photoelectric sensor is installed on the frame above the furrow opener. To sum up, the present invention can perform target variable hole depth fertilization operations according to the different growth states of each large-plant-spacing crop in the field, and has the advantages of strong adaptability, simple structure, high working efficiency and labor saving, etc.

This invention discloses a method for soil salinity inversion based on the fusion of remote sensing features at multiple time scales, comprising the following steps: A1 field sampling and soil conductivity measurement; A2 remote sensing data preprocessing and spectral index calculation; A3 environmental covariate acquisition and preprocessing; A4 determination of the optimal time scale feature combination; A5 feature variable screening and optimization; A6 soil salinity inversion model construction; fusing remote sensing features at different time scales, and constructing a soil salinity remote sensing inversion model based on the optimal feature combination using a random forest algorithm. By systematically integrating the instantaneous response features of single-period images with the features of seasonal composite images, the information of remote sensing data at different time scales is fully exploited, solving the problems of single time scale of remote sensing features, insufficient information utilization, and difficulty in coordinating multi-scale features in traditional modeling processes. This improves the model's ability to characterize the spatial distribution of soil salinity and its prediction accuracy, providing more scientific and reliable technical support for remote sensing monitoring of salinized areas.

The invention discloses a soil quality monitoring system and method for citrus planting, and belongs to the technical field of soil quality monitoring, and the system comprises a soil salinity accumulation judgment module, a soil salinity accumulation adjustment module and a citrus absorption efficiency analysis module. By solving the problem of salt accumulation caused by continuous increase of soil conductivity and adjusting the problem of unbalanced citrus absorption efficiency caused by fluctuation of pH values of different plots, the quality and yield of the planted citrus are guaranteed, more efficient resource utilization is achieved, soil health is maintained, and the absorption efficiency of citrus root systems is improved.

The present invention provides a method and system for constructing a rice growth model based on salt stress, relating to the technical field of growth model construction. The method first sets up monitoring points in a planting sample area and obtains soil conductivity data at different depths using multi-depth soil conductivity sensors and the Kriging interpolation method. Root density, multispectral remote sensing imagery, and leaf area index are collected to calculate the canopy salt stress index. The sodium adsorption ratio is determined by measuring relevant ion concentrations, and a salt stress coefficient is established by combining soil conductivity and irrigation volume. The canopy and soil stress indicators are integrated to generate a comprehensive stress index, and a salt feedback term is introduced to characterize crop compensation capacity. Finally, a hybrid machine learning model is constructed using a convolutional neural network and a long-short-term memory network to achieve dynamic prediction of rice growth. The present invention achieves multidimensional salt stress quantification in the soil-crop system, providing decision support for salinization control in precision agriculture.

The present invention relates to a method for detecting the compaction degree of soil based on the response surface method. First, indoor calibration tests are carried out on the in-situ tested soil to establish a second-order response surface model of the dielectric constant, conductivity, and maximum penetration resistance of the soil varying with the mass moisture content and dry density. Secondly, the correlation between the conductivity and dielectric constant of the soil is studied, a correction model of the soil conductivity is established and the conductivity correction value is calculated. Then, the measured dielectric constant, measured maximum penetration resistance, and conductivity correction value are substituted into the second-order response surface model to establish an objective function with the minimum root mean square error of the measured value and the calculated value. Finally, the particle swarm optimization algorithm is used for inversion to obtain the mass moisture content and dry density of the soil, and the compaction degree of the soil is calculated. The testing method of the present invention can quickly and accurately detect the compaction degree of the soil after field rolling, measure the mass moisture content and dry density of the soil, and is applicable to different engineering filled soils.

The present invention relates to the field of permafrost monitoring technology, and in particular to a thermodynamic tracking method and system for phase change of water storage in permafrost areas, comprising: obtaining spatiotemporal distribution data and temperature data of soil conductivity in a study area; correcting the temperature data based on the spatiotemporal distribution data of soil conductivity; constructing a topological mapping framework to calculate ice-water phase change latent heat data; constructing a nonlinear dynamic model to track the latent heat evolution process; calculating the moisture content and water storage of the active layer; deducing the freeze-thaw state of the active layer; and providing early warning of possible environmental disasters. Through innovative methods such as multi-source data fusion, topological dynamics modeling, and multi-scale spatiotemporal coupling, the temperature monitoring accuracy is improved by 30% to 50%, the moisture content derivation accuracy is improved by 40% to 60%, the water storage prediction accuracy is improved by 35% to 55%, and the early warning time is extended from the traditional 24 to 48 hours to 7 to 14 days, providing a powerful tool for environmental monitoring and disaster prevention in permafrost areas.

The application discloses a soil salinity inversion method and system based on multi-modal remote sensing data fusion, a device and a storage medium, and is applied to the technical field of soil quality monitoring.The method comprises the following steps: acquiring radar and optical remote sensing data of a soil salinity area to be inversed, and performing conductivity determination as an inversion index of soil salinity; acquiring multi-modal remote sensing features based on radar and optical remote sensing data fusion, combining the radar and optical remote sensing data, and based on a random forest algorithm, using a recursive feature elimination method to optimize the remote sensing feature combination, using cross validation to evaluate the model performance of the remote sensing feature combination, and obtaining an optimal remote sensing feature combination; based on the optimal remote sensing feature combination, a soil conductivity prediction model based on the random forest algorithm is constructed and trained, inputting the data to be measured into the conductivity prediction model after hyperparameter adjustment, and the soil salinity inversion is completed.The application realizes more accurate inversion of soil salinity under the interaction influence of complex environment and human factors.