Search

Accurate production estimates, months before the harvest, are crucial for all parts of the food supply chain, from farmers to governments. While methods have been developed to use satellite data to monitor crop development and production, they typically rely on official crop statistics or ground-based data, limiting their application to the regions where they were calibrated. To address this issue, a new method called VeRsatile Crop Yield Estimator (VeRCYe) has been developed to estimate wheat yield at the pixel and field levels using satellite data and process-based crop models. The method uses the Leaf Area Index (LAI) as the linking variable between remotely sensed data and APSIM crop model simulations. In this process, the sowing dates of each field were detected (RMSE = 2.6 days) using PlanetScope imagery, with PlanetScope and Sentinel-2 data fused into a daily 3 m LAI dataset, enabling VeRCYe to overcome the traditional trade-off between satellite data that has either high temporal or high spatial resolution. The method was evaluated using 27 wheat fields across the Australian wheatbelt, covering a wide range of pedo-climatic conditions and farm management practices across three growing seasons. VeRCYe accurately estimated field-scale yield (R2 = 0.88, RMSE = 757 kg/ha) and produced 3 m pixel size yield maps (R2 = 0.32, RMSE = 1213 kg/ha). The method can potentially forecast the final yield (R2 = 0.78–0.88) about 2 months before the harvest. Finally, the harvest dates of each field were detected from space (RMSE = 2.7 days), indicating when and where the estimated yield would be available to be traded in the market. VeRCYe can estimate yield without ground calibration, be applied to other crop types, and used with any remotely sensed LAI information. This model provides insights into yield variability from pixel to regional scales, enriching our understanding of agricultural productivity. [ABSTRACT FROM AUTHOR]

This study focuses on creating predictive models for sugarcane yield in Bihar, utilizing various biometrical characteristics. The research involved collecting observations on specific plant biometrical traits from 50 farmers' fields of Samastipur, West Champaran and East Champaran Districts of Bihar. Simple random sampling was employed for field selection. Various regression analyses were conducted to identify the optimal combination. The accuracy of the model was assessed by comparing the actual yield from 10% of the observations not used in model development with their predicted values. The results demonstrated a close resemblance, with a margin of error ranging from 5.91% to 8.36%. The forecasted sugarcane yield for Bihar, based on the proposed model, is 847.82 q/ha. [ABSTRACT FROM AUTHOR]

Cotton is a major economic crop predominantly cultivated under rainfed situations. The accurate prediction of cotton yield invariably helps farmers, industries, and policy makers. The final cotton yield is mostly determined by the weather patterns that prevail during the crop growing phase. Crop yield prediction with greater accuracy is possible due to the development of innovative technologies which analyses the bigdata with its high-performance computing abilities. Machine learning technologies can make yield prediction reasonable and faster and with greater flexibility than process based complex crop simulation models. The present study demonstrates the usability of ML algorithms for yield forecasting and facilitates the comparison of different models. The cotton yield was simulated by employing the weekly weather indices as inputs and the model performance was assessed by nRMSE, MAPE and EF values. Results show that stacked generalised ensemble model and artificial neural networks predicted the cotton yield with lower nRMSE, MAPE and higher efficiency compared to other models. Variable importance studies in LASSO and ENET model found minimum temperature and relative humidity as the main determinates of cotton yield in all districts. The models were ranked based these performance metrics in the order of Stacked generalised ensemble > ANN > PCA ANN > SMLR ANN > LASSO> ENET > SVM > PCA SMLR > SMLR SVM > SMLR. This study shows that stacked generalised ensembling and ANN method can be used for reliable yield forecasting at district or county level and helps stakeholders in timely decision-making. [ABSTRACT FROM AUTHOR]

The olive tree is one of the most common type of cultivation in the Mediterranean area, having high economic and social importance. The Alentejo region, Portugal, is an area with a high presence of olive groves, which in 2022 accounted for 201,474 hectares. The aim of this study was to assess the relationship between olive pollen, weather data, and olive tree production, between the years 2002 and 2022. Pollen data were obtained from an urban station located in Évora, in the Alentejo region, and were used to calculate several metrics, such as the Pollen Season Duration (PSD), Seasonal Pollen Index (SPIn), peak value, and weekly pollen accumulation values. Monthly minimum, maximum, and mean temperature and precipitation sums were obtained from the E-OBS observational dataset. Considering the relationship between pollen/weather and olive production, mutual information and correlation analyses were conducted. Subsequently, several machine learning algorithms were trained using pollen and weather datasets, and we obtained suitable forecast models for olive tree production after cross-validation. The results showed high variability in pollen concentrations in Évora over the years. Complex associations were found, with certain weeks of pollen accumulation showing significant mutual information with olive production, particularly during June. The analyzed linear correlation coefficients remained generally low, underscoring the challenge of predicting olive production based on linear relationships. Among the machine learning algorithms employed to predict olive production, Decision Trees, Extreme Gradient Boosting, and Gradient Boosting Regressor were the most robust performers (r2 > 0.70), while linear models displayed a subpar performance (r2 < 0.5), emphasizing the complexity of this approach. These models highlight the roles of maximum and minimum temperatures during March and May and pollen accumulation during the second half of June. The developed models may be used as decision-support tools by growers and stakeholders to further enhance the sustainability of the thriving olive sector in southern Portugal. [ABSTRACT FROM AUTHOR]

Crop yield forecasting during an ongoing season is crucial to ensure food security and commodity markets. For this reason, here, a scalable approach to forecast corn yields at the field-level using machine learning and satellite imagery from Sentinel-2 and Landsat missions is proposed. The model, evaluated on 1319 corn fields in the U.S. Corn Belt from 2017 to 2022, integrates biophysical parameters from Sentinel-2, Land Surface Temperature (LST) from Landsat, and agroclimatic data from ERA5 reanalysis dataset. Resampling the time series over thermal time significantly enhances predictive performance. The addition of LST to our model further improves in-season yield forecasting, through its capacity to detect early drought, which is not immediately visible to optical sensors such as the Sentinel-2. Finally, we propose a new two-stage machine learning strategy to mitigate early season partially available data. It consists in extending the current time series on the basis of complete historical data and adapting the model inference according to the crop progress. [ABSTRACT FROM AUTHOR]

Accurate, non-destructive forecasting of carrot yield is difficult due to its subterranean growing habit. Furthermore, the timing of forecasting usually occurs when the crop is mature, limiting the opportunity to implement alternative management decisions to improve yield (during the growing season). This study aims to improve the accuracy of carrot yield forecasting by exploring time series and multivariate approaches. Using Sentinel-2 satellite imagery in three Australian vegetable regions, we established a time series of carrot phenological stages (PhS) from 'days after sowing' (DAS) to enhance prediction timing. Numerous vegetation indices (VIs) were analyzed to derive temporal growth patterns. Correlations with yield at different PhS were established. Although the average root yield (t ha−1) did not significantly differ across the regions, the temporal VI signatures, indicating different regional crop growth trends, did vary as well as the PhS at when the maximum correlation with yield occurred ( P h S R 2 max ) with two of the regions producing a delayed P h S R 2 max (i.e. 90–130 DAS). The best multivariate model was identified at 70 DAS, extending the forecasting window before harvest between 20 to 60 days. The performance of this model was validated with new crops producing an average error of 16.9 t ha−1 (27% of total yield). These results demonstrate the potential of the model at such early stage under varying growing conditions offering growers and stakeholders the chance to optimize farming practices, make informed decisions on selling, harvesting, and labor planning, and adopt precision agriculture methods. [ABSTRACT FROM AUTHOR]

A neural network was developed to predict the effect of phosphorus on spring wheat yields. The focus is on the neural network, including its structure, parameters, training methods and results related to phosphorus effects on spring wheat yields. An algorithm for developing a neural network model is also presented. The study was conducted to address the critical need for developing a neural network to predict the effect of phosphorus on spring wheat yields in the Republic of Kazakhstan. For data analysis, input data were used that cover the period from 2012 to 2022, including climatic indicators, regional features and phosphorus application. The target variable is spring wheat yield. To ensure the accuracy of the study, the data were preprocessed and standardized, and an outlier and variance analysis was performed. The developed neural network was trained and tested to obtain the best results. The mean squared error was used as a metric for evaluating the quality of forecasting. Additionally, indicators such as mean absolute error and coefficient of determination were considered. The results of the study showed an MSE of 7.12, indicating that the model agrees well with the data and makes accurate predictions, which also suggests its practical relevance. The correlation analysis of the features showed that phosphorus application and spring wheat yield have a positive relationship. These results can be very useful for agriculture and farming enterprises, as they allow optimizing phosphorus application to the soil and increasing wheat yields [ABSTRACT FROM AUTHOR]

Yield forecasting is of immeasurable value in modern viticulture to optimize harvest scheduling and quality management. Traditionally, this task is carried out through manual and destructive sampling of production components and their accurate assessment is expensive, time-consuming, and error-prone, resulting in erroneous projections. The number of inflorescences and flowers per vine is one of the main components and serves as an early predictor. The adoption of new non-invasive technologies can automate this task and drive viticulture yield forecasting to higher levels of accuracy. In this study, different Single Stage Instance Segmentation models from the state-of-the-art You Only Look Once (YOLO) family, such as YOLOv5 and YOLOv8, were benchmarked on a dataset of RGB images for grapevine inflorescence detection and segmentation, with the aim of validating and subsequently implementing the solution for counting the number of inflorescences and flowers. All models obtained promising results, with the YOLOv8s and the YOLOv5s models standing out with an F1-Score of 95.1% and 97.7% for the detection and segmentation tasks, respectively. Moreover, the low inference times obtained demonstrate the models' ability to be deployed in real-time applications, allowing for non-destructive predictions in uncontrolled environments. [ABSTRACT FROM AUTHOR]

The olive tree is one of the most common type of cultivation in the Mediterranean area, having high economic and social importance. The Alentejo region, Portugal, is an area with a high presence of olive groves, which in 2022 accounted for 201,474 hectares. The aim of this study was to assess the relationship between olive pollen, weather data, and olive tree production, between the years 2002 and 2022. Pollen data were obtained from an urban station located in Évora, in the Alentejo region, and were used to calculate several metrics, such as the Pollen Season Duration (PSD), Seasonal Pollen Index (SPIn), peak value, and weekly pollen accumulation values. Monthly minimum, maximum, and mean temperature and precipitation sums were obtained from the E-OBS observational dataset. Considering the relationship between pollen/weather and olive production, mutual information and correlation analyses were conducted. Subsequently, several machine learning algorithms were trained using pollen and weather datasets, and we obtained suitable forecast models for olive tree production after cross-validation. The results showed high variability in pollen concentrations in Évora over the years. Complex associations were found, with certain weeks of pollen accumulation showing significant mutual information with olive production, particularly during June. The analyzed linear correlation coefficients remained generally low, underscoring the challenge of predicting olive production based on linear relationships. Among the machine learning algorithms employed to predict olive production, Decision Trees, Extreme Gradient Boosting, and Gradient Boosting Regressor were the most robust performers (r2 > 0.70), while linear models displayed a subpar performance (r2 < 0.5), emphasizing the complexity of this approach. These models highlight the roles of maximum and minimum temperatures during March and May and pollen accumulation during the second half of June. The developed models may be used as decision-support tools by growers and stakeholders to further enhance the sustainability of the thriving olive sector in southern Portugal.

Due to the sharp changes in climatic conditions in Western Siberia, the most pressing problem is food security associated with forecasting crop yields. There is a need to estimate the natural wetness of the area on the basis of agroclimatic indicators, among which the sum of active air temperatures and precipitation is currently the most widely used. Background. However, for a comprehensive assessment of the wetness of the territory, it is necessary to take into account the climate energy resources associated with evaporation of different time resolutions (day, decades, months, vegetation period, year). The initial meteorological parameters are described in the form of poorly structured information of a large volume. Therefore, various technologies and algorithms of machine processing are used in the work. Purpose. The application of big data technologies to assess the natural moisture of the territory Materials and methods. With the help of the high-level Python programming language and engineering libraries, a comprehensive assessment of the territory was carried out using the example of Mirny of the Kochenevsky District of the Novosibirsk Region in the context of long-term average data and two years 2019 and 2020. That the use of machine processing technologies related to NoSQL data requests, creation of data set and big data slices allows to store and process meteorological parameters using cloud services of different time resolution. This makes it possible to significantly reduce the time for a comprehensive assessment of the territory according to agroclimatic parameters. As a result of the work, precipitation distribution, temperature, relative air humidity, evaporability, humidification coefficients (Ivanov-Vysotsky and Selyaninov hydrothermal coefficient) were obtained. Results. The paper proposes to use technologies of big data processing using Python, including pre-processing of poorly structured hydrometeorological data, execution of NoSQL queries, compilation of summary reports on agroclimatic parameters. Pre-processing consists of processing hourly meteorological data, filling gaps in the data, making slices in big data to process multi-temporal queries (day, month, growing season, year). By the example of Mirny farm in Kochenevsky district of Novosibirsk region (Russian Federation), big data processing was performed to calculate agroclimatic parameters to assess the natural moisture content of the area and yield forecasting. Conclusion. The practical significance of the work is as follows: - the application of big data processing technologies has significantly reduced the time for the labor-intensive process of assessing agrometeorological parameters; - obtained aggregated meteorological parameters of different temporal resolution (hours, days, decades, months) allowed us to identify a strong variability of agroclimatic conditions for the territory of Mirny farm Kochenevsky district, located in the forest-steppe zone of Western Siberia; - perform an integral assessment of agroclimatic conditions by calculating the integral indices of moisture, climate continentality, and agroclimatic potential.

Abstract Due to rapid population growth and the limitation of land resources, the sustainability of agricultural ecosystems has attracted more attention all over the world. Human activities will alter the components of the atmosphere and lead to climate change, which consequently affects crop production badly. In this context, wheat is considered an important crop and ranks as one of the top strategic crops globally. The main objective of this research is to develop a new approach (a weighted climatic suitability index) for evaluating the climate suitability for wheat production. The specific objectives are to project the impact of future climate change on wheat suitability using three models based on WCSI and CMIP6-based projections and to identify the most vulnerable area to climate change and productivity reduction. The climatic criteria for wheat production were selected and classified into eight indicators based on the Sys' scheme and the FAO framework, and then the weighted overlay approach was used in conjunction with the analytic hierarchy process. To confirm the reliability of the integrated WCSI, we determined the nonlinear curve fitting of integrated WCSI-induced wheat yields by the exponential growth equation. Finally, the CMIP6-GCMs projected from three shared socioeconomic pathways were used for WCSI mapping and predicting wheat yields in the short and long term (Southern Syria was selected as a case study). The results show that the nonlinear correlation between wheat yields and the integrated WCSI was 0.78 (R2 = 0.61) confirming the integrated WCSI's reliability in reflecting yield variation caused by climate suitability. The results indicated that WCSI for wheat will be lower over the study area during 2080–2100 compared to the current climate. During 2080–2100, the wheat yield is projected to decrease by 0.2–0.8 t. ha−1 in the western parts of the study area. The findings of this study could be used to plan and develop adaptation strategies for sustainable wheat production in the face of projected climate change. The results of the study will also help in the strategic planning of wheat production in Syria under the projected climate. The results of this research are limited to small areas as a case study, although they are not relevant to similar regions worldwide. However, the study employs novel analytical methods that can be used broadly.

Ukraine was one of the main exporters of plant products. However, as a result of the aggression, the country's agriculture has suffered greatly, export volumes are decreasing, which may provoke a shortage of agricultural products on world markets. It is impossible to assess crop yield and forecast the harvest volume locally, as the collection of information has become difficult due to the active conduct of hostilities and the occupation of a large part of the territories. Therefore, it is necessary to use land remote sensing data to assess crop yield. In this research, we will build regression models based on a random forest for each region of Ukraine to estimate crop yield based on 16-day composites of the NDVI time series during the summer vegetation period from Sentinel-2 (10m) and MODIS (500m) satellites, involving in the calculation NDVI crop maps. The official yield of maize, sunflower, soybean, rapeseed, and wheat for the years 2016-2021 was used as training data. According to the results of the analysis, models based on NDVI from the MODIS satellite showed better accuracy (relative error within 8-18%), but models based on NDVI data from Sentinel-2 better described the variance of the predicted yield. During the research, we found a sharp drop in land productivity indicators compared to the productivity of 2021 for the territories of central, southern and eastern Ukraine. According to our estimates based on MODIS data, the average yield at the country level is expected to be 40.98 t/ha for wheat, 57.66 t/ha for maize, 23.57 t/ha for sunflower, 21.06 t/ha for soybeans, 21.15 t/ha for rapeseed. Estimates based on Sentinel-2 data: 43.22 t/ha for wheat, 71.93 t/ha for maize, 26.86 t/ha for sunflower, 22.94 t/ha for soybeans, 28.23 t/ha for rapeseed.

Crop yield forecasting during an ongoing season is crucial to ensure food security and commodity markets. For this reason, here, a scalable approach to forecast corn yields at the field-level using machine learning and satellite imagery from Sentinel-2 and Landsat missions is proposed. The model, evaluated on 1319 corn fields in the U.S. Corn Belt from 2017 to 2022, integrates biophysical parameters from Sentinel-2, Land Surface Temperature (LST) from Landsat, and agroclimatic data from ERA5 reanalysis dataset. Resampling the time series over thermal time significantly enhances predictive performance. The addition of LST to our model further improves in-season yield forecasting, through its capacity to detect early drought, which is not immediately visible to optical sensors such as the Sentinel-2. Finally, we propose a new two-stage machine learning strategy to mitigate early season partially available data. It consists in extending the current time series on the basis of complete historical data and adapting the model inference according to the crop progress.

This study presents a comprehensive evaluation of seasonal, locational, and varietal variations in canopy reflectance responses in 315 commercial citrus blocks from three major growing regions in Australia. The dataset includes three different citrus types (Mandarin, Navel, Valencia) and 26 varieties. The aim is to utilize this combined information to better understand yield variation and develop improved forecasting models. Landsat satellite data spanning from October 2006 to February 2021 (1419 tiles) were used to derive reflectance values, and calculate four vegetation indices (NDVI, GNDVI, LSWI, and GCVI), for each citrus block. These indices were then analyzed alongside corresponding yield data, which consisted of 3660 individual yield records dating back to 2007. Two temporal resolutions were incorporated as predictors: spatio-temporal vegetation index time series (TS) aggregated every two months and annual time series of historical block-yield records. Six statistical and machine learning algorithms were calibrated using a leave-one-year-out cross-validation approach (LOYO CV) and validated for one-year forward prediction over a five-year period (2017–2021). The results highlight significant yield variations across years, alternate bearing patterns, and spatio-temporal changes in reflectance profiles influenced by seasonal conditions, varietal characteristics, and locations. The support vector machine (SVM) algorithm with a radial basis function kernel consistently outperformed other algorithms, indicating a non-linear relationship between citrus yield and predictors. The SVM model achieved an RMSE of 15.5 T ha−1, R2 of 0.88, MAE of 12.1 T ha−1, and MAPE of 29% in predicting block-yield across farms, varieties, and seasons. These prediction accuracy metrics demonstrate an improvement over current forecasting methods. Notably, the proposed approach utilizes freely available imagery, provides forecasts between two to nine months before harvest, and eliminates the need for infield counting of fruit load for image calibration. This approach provides an improved method for understanding seasonal yield variation and quantifying citrus block-yield, offering valuable insights for growers in harvest logistics, labor allocation, and resource management.

Despite their productivity, fir and beech forests in Greece lack site index curves. In this work, site index curves for Fagus sylvatica and Abies borisii-regis in central Greece were developed. Thirty plots were randomly established in the mixed stands of F. sylvatica–A. borisii-regis in Aspropotamos, central Greece, and two dominant trees, one from each species, were randomly selected and cut. Height–age measurements were collected through stem analysis. These data were used to develop site index curves for each species. The site index curves illustrate a growth rate difference between the two species, specifically in the worst sites, with fir growing faster than beech. Additionally, as trees age, the growth difference between the two species in the best sites decreases. Based on these results, F. sylvatica is found to be more site-sensitive than A. borisii-regis. In the new adverse conditions of global warming, an increased knowledge of the site sensitivity of the two species will help to develop appropriate treatments for the conservation of the studied mixed stands, or at least to minimize negative impacts. [ABSTRACT FROM AUTHOR]

The article provides an overview of the accuracy of various yield forecasting algorithms and offers a detailed explanation of the models and machine learning algorithms that are required for crop yield forecasting. A unified crop yield forecasting methodology is developed, which can be adjusted by adding new indicators and extensions. The proposed methodology is based on remote sensing data taken from free sources. Experiments were carried out on crops of cereals, legumes, oilseeds and forage crops in eastern Kazakhstan. Data on agricultural lands of the experimental farms were obtained using processed images from Sentinel-2 and Landsat-8 satellites (EO Browser) for the period of 2017–2022. In total, a dataset of 1600 indicators was collected with NDVI and MSAVI indices recorded at a frequency of once a week. Based on the results of this work, it is found that yields can be predicted from NDVI vegetation index data and meteorological data on average temperature, surface soil moisture and wind speed. A machine learning programming language can calculate the relationship between these indicators and build a neural network that predicts yield. The neural network produces predictions based on the constructed data weights, which are corrected using activation function algorithms. As a result of the research, the functions with the highest prediction accuracy during vegetative development for all crops presented in this paper are multi-layer perceptron, with a prediction accuracy of 66% to 99% (85% on average), and polynomial regression, with a prediction accuracy of 63% to 98% (82% on average). Thus, it is shown that the use of machine learning and neural networks for crop yield prediction has advantages over other mathematical modelling techniques. The use of machine learning (neural network) technologies makes it possible to predict crop yields on the basis of relevant data. The individual approach of machine learning to each crop allows for the determination of the optimal learning algorithms to obtain accurate predictions. [ABSTRACT FROM AUTHOR]

This study uses five machine learning algorithms (Stochastic gradient descent (SGD), Decision tree, Random forest, Gradient boosting decision tree (GBDT), and Convolutional neural networks (CNN)) to explore their prediction effects on China's stock market. It constructs a monthly rolling model for stock return prediction. Selecting stocks of the CSI 300 index from January to June 2021 as specific monthly samples and classifying three factors – fundamentals, volatility(risk) and technical indicators, the results demonstrate that (1) machine learning brings favorable investment returns in simulated quantitative trading of China's A-share market (2) the technical indicator factor is the most valuable, with the momentum technical factor having greatest influence, followed by the volatility (risk) factor and fundamental factors. Therefore, this study has a critical reference value and is significant in guiding yield forecasting in intricate stock markets. [ABSTRACT FROM AUTHOR]

The aim of this study was to determine the usefulness of artificial neural networks (ANN) in the process of forecasting the yield of hemp seeds (Cannabis sativa L.) of the Henola variety. The field experiments (various doses of mineral fertilization, sowing date, row spacing) results were also used to generate neural models. The highest straw (15.90 Mg∙ha−1) and seed (2.93 Mg∙ha−1) yield were obtained for the highest dose of mineral fertilization and sowing date at the turn of April and May in Wielkopolska Region resulted in the highest yields of both straw (14.70 Mg∙ha−1) and seeds (2.66 Mg∙ha−1). As a result of the conducted research, two linear models of ANN s were generated. The 4: 8–1: 1 model, used to forecast the seed yield was characterized by an accuracy of nearly 91%, and the RMSPE error less than 34%. The second model, the 4: 4–1: 1 network, was used to forecast the straw yield and had The test quality nearly 74%, and the RMSPE error 26%.

Due to rapid population growth and the limitation of land resources, the sustainability of agricultural ecosystems has attracted more attention all over the world. Human activities will alter the components of the atmosphere and lead to climate change, which consequently affects crop production badly. In this context, wheat is considered an important crop and ranks as one of the top strategic crops globally. The main objective of this research is to develop a new approach (a weighted climatic suitability index) for evaluating the climate suitability for wheat production. The specific objectives are to project the impact of future climate change on wheat suitability using three models based on WCSI and CMIP6-based projections and to identify the most vulnerable area to climate change and productivity reduction. The climatic criteria for wheat production were selected and classified into eight indicators based on the Sys' scheme and the FAO framework, and then the weighted overlay approach was used in conjunction with the analytic hierarchy process. To confirm the reliability of the integrated WCSI, we determined the nonlinear curve fitting of integrated WCSI-induced wheat yields by the exponential growth equation. Finally, the CMIP6-GCMs projected from three shared socioeconomic pathways were used for WCSI mapping and predicting wheat yields in the short and long term (Southern Syria was selected as a case study). The results show that the nonlinear correlation between wheat yields and the integrated WCSI was 0.78 (R2 = 0.61) confirming the integrated WCSI's reliability in reflecting yield variation caused by climate suitability. The results indicated that WCSI for wheat will be lower over the study area during 2080–2100 compared to the current climate. During 2080–2100, the wheat yield is projected to decrease by 0.2–0.8 t. ha−1 in the western parts of the study area. The findings of this study could be used to plan and develop adaptation strategies for sustainable wheat production in the face of projected climate change. The results of the study will also help in the strategic planning of wheat production in Syria under the projected climate. The results of this research are limited to small areas as a case study, although they are not relevant to similar regions worldwide. However, the study employs novel analytical methods that can be used broadly. [ABSTRACT FROM AUTHOR]

Accurate preharvest yield estimation is an important issue for agricultural planning purposes and precision farming. Machine learning (ML) based on readily obtained information on the cropping system, typically including spectral reflectance measurements, is an essential approach for achieving practical solutions. We tested in a 9‐year soil compaction experiment the accuracy of ML‐based yield predictions made up to 2 months before harvest from a Ratio Vegetation Index (RVI) and recordings of precipitation and reference evapotranspiration. The applied data set comprises 224 combinations of plots and years with measured grain yields in the range of 4.22–9.34 Mg/ha. The best ML model [i.e., with the smallest mean absolute error (MAE)] was selected automatically by the AutoML interface included in the R program package H2O. Its cross‐validated predictions made on June 30 more than 1 month before harvest showed an MAE of 0.38 Mg/ha when trained on all data from all years except the one under consideration. MAE increased to about 0.68 Mg/ha when determined 3 weeks earlier on June 10. MAE values in the range of 0.32–0.42 Mg/ha were obtained for predictions made on June 30 when based on data from at least six consecutive years; however, MAE showed no generally decreasing trend with the number of years. Yield estimations were robust towards a considerable soil variation observed within the experimental area due in part to the experimental treatments. The results show a potential of making yield predictions in barley 1–2 months before harvest, which, however, is not sufficiently early to support decisions on top‐dress N fertilization. [ABSTRACT FROM AUTHOR]

Early forecasting of crop yield from field to region is important for stabilizing markets and safeguarding food security. Producing a precise forecasting result with fewer inputs is an ongoing goal for the large-area yield evaluation. We present one approach of yield prediction for maize that was explored by incorporating remote-sensing-derived land surface temperature (LST) and field in-season data into a series of logistic models with only a few parameters. Continuous observation data of maize were utilized to calibrate and validate the corresponding logistic models for regional biomass estimating based on field temperatures (including crop canopy temperature (Tc)) and relative dry/fresh biomass accumulation. The LST maps from MOD11A1 products, which are considered to be matched as Tc in large irrigation districts, were assimilated into the validated models to estimate the biomass accumulation. It was found that the temporal-scale difference between the instantaneous LST and the daily average value of field-measured Tc was eliminated by data normalization method, indicating that the normalized LST could be input directly into the model as an approximation of the normalized Tc. Making one observed biomass in-season as the driving force, the maximum of dry/fresh biomass accumulation (DBA/FBA) at harvest could be estimated. Then, grain yield forecasting could be achieved according to the local harvest index of maize. Silage and grain yields were evaluated reasonably well compared with field observations based on the regional map of LST values obtained in 2017 in Changchun, Jilin Province, China. Here, satisfactory grain and silage yield forecasting was provided by assimilating once measured value of DBA/FBA at the middle growth period (early August) into the model in advance of harvest. Meanwhile, good results were obtained in the application of this approach using field data in 2016 to predict grain yield ahead of harvest in the Jiefangzha sub-irrigation district, Inner Mongolia, China. This study demonstrated that maize yield can be forecasted accurately prior to harvest by assimilating remote-sensing-derived LST and field data into the logistic models at a regional scale considering the spatio-temporal scale extension of ground information and crop dynamic growth in real time. [ABSTRACT FROM AUTHOR]

Crop yield forecasting before harvesting is critical for the creation, implementation, and optimization of policies related to food safety as well as for agro-product storage and marketing. Crop growth and development are influenced by the weather. Therefore, models using weather variables can provide reliable predictions of crop yields. It can be tough to select the best crop production forecasting model. Therefore, in this study, five alternative models, viz., stepwise multiple linear regression (SMLR), an artificial neural network (ANN), the least absolute shrinkage and selection operator (LASSO), an elastic net (ELNET), and ridge regression, were compared in order to discover the best model for rice yield prediction. The outputs from individual models were used to build ensemble models using the generalized linear model (GLM), random forest (RF), cubist and ELNET methods. For the previous 21 years, historical rice yield statistics and meteorological data were collected for three districts under three separate agro-climatic zones of Chhattisgarh, viz., Raipur in the Chhattisgarh plains, Surguja in the northern hills, and Bastar in the southern plateau. The models were calibrated using 80% of these datasets, and the remaining 20% was used for the validation of models. The present study concluded that for rice crop yield forecasting, the performance of the ANN was good for the Raipur ( R c a l 2 = 1, R v a l 2 = 1 and R M S E c a l = 0.002, R M S E v a l = 0.003) and Surguja ( R c a l 2 = 1, R v a l 2 = 0.99 and R M S E c a l = 0.004, R M S E v a l = 0.214) districts as compared to the other models, whereas for Bastar, ELNET ( R c a l 2 = 90, R v a l 2 = 0.48) and LASSO ( R c a l 2 = 93, R v a l 2 = 0.568) performed better. The performance of the ensemble model was better compared to the individual models. For Raipur and Surguja, the performance of all the ensemble methods was comparable, whereas for Bastar, random forest (RF) performed better, with R2 = 0.85 and 0.81 for calibration and validation, respectively, as compared to the GLM, cubist, and ELNET approach. [ABSTRACT FROM AUTHOR]

Remote sensing methods based on UAV and hand-held devices as well have been used to assess the response to nitrogen and sulfur fertilization of hypoallergenic genotypes of winter wheat. The field experiment was conducted using the split-split-plot design with three repetitions. The first factor was the two genotypes of winter wheat specified as V1 (without allergic protein) and V2 (with allergic protein), and the second factor was three doses of sulfur fertilization: 0, 20 and 40 kg S per ha. The third factor consisted of six doses of nitrogen fertilization: 0, 40, 60, 80, 100 and 120 kg N·ha−1. Monitoring the values of the indicators depending on the level of nitrogen and sulfur fertilization allowed the results to be used in yield forecasting, assessment of plant condition, LAI value, nutritional status in the cultivation of wheat. The maximum yield should be expected at doses of 94 and 101 kg N ha−1 for genotypes V1 and V2, respectively, giving yields of 5.39 and 4.71 Mg ha−1. On the basis of the tested vegetation indices, the highest doses of N should be applied using the normalized difference RedEdge (NDRE), and the lowest ones based on the enhanced vegetation index (EVI), and, in the latter case, a reduction in yield of more than 200 kg ha−1 in the V2 genotype should be taken into account. [ABSTRACT FROM AUTHOR]

Dust accumulation on the photovoltaic system adversely degrades its power conversion efficiency (PCE). Focusing on residential installations, dust accumulation on PV modules installed in tropical regions may be vulnerable due to lower inclination angles and rainfall that encourage dust settlement on PV surfaces. However, most related studies in the tropics are concerned with studies in the laboratory, where dust collection is not from the actual field, and an accurate performance prediction model is impossible to obtain. This paper investigates the dust-related degradation in the PV output performance based on the developed Artificial Neural Network (ANN) predictive model. For this purpose, two identical monocrystalline modules of 120 Wp were tested and assessed under real operating conditions in Melaka, Malaysia (2.1896° N, 102.2501° E), of which one module was dust-free (clean). At the same time, the other was left uncleaned (dusty) for one month. The experimental datasets were divided into three sets: the first set was used for training and testing purposes, while the second and third, namely Data 2 and Data 3, were used for validating the proposed ANN model. The accuracy study shows that the predicted data using the ANN model and the experimentally acquired data are in good agreement, with MAE and RMSE for the cleaned PV module are as low as 1.28 °C, and 1.96 °C respectively for Data 2 and 3.93 °C and 4.92 °C respectively for Data 3. Meanwhile, the RMSE and MAE for the dusty PV module are 1.53°C and 2.82 °C respectively for Data 2 and 4.13 °C and 5.26 °C for Data 3. The ANN predictive model was then used for yield forecasting in a residential installation and found that the clean PV system provides a 7.29 % higher yield than a dusty system. The proposed ANN model is beneficial for PV system installers to assess and anticipate the impacts of dust on the PV installation in cities with similar climatic conditions.

The aim of this study was to determine the usefulness of artificial neural networks (ANN) in the process of forecasting the yield of hemp seeds (Cannabis sativa L.) of the Henola variety. The field experiments (various doses of mineral fertilization, sowing date, row spacing) results were also used to generate neural models. The highest straw (15.90 Mg∙ha-1) and seed (2.93 Mg∙ha-1) yield were obtained for the highest dose of mineral fertilization and sowing date at the turn of April and May in Wielkopolska Region resulted in the highest yields of both straw (14.70 Mg∙ha-1) and seeds (2.66 Mg∙ha-1). As a result of the conducted research, two linear models of ANN s were generated. The 4: 8-1: 1 model, used to forecast the seed yield was characterized by an accuracy of nearly 91%, and the RMSPE error less than 34%. The second model, the 4: 4-1: 1 network, was used to forecast the straw yield and had The test quality nearly 74%, and the RMSPE error 26%. [ABSTRACT FROM AUTHOR]

Crop yield forecasting is the art of predicting yield before harvest and is crucial for sound planning and policy making at various levels. Rapeseed and mustard (R&M) is the predominant oilseed crop in Assam and is very much sensitive to climatic factors compared to other crops grown during rabi season. In the context of recent climate variability observed in the Brahmaputra valley, development of efficient yield forecasting models for R&M based on weather parameters would certainly help the policy makers in formulating appropriate policies and decision-making. The present study was undertaken to develop R&M pre-harvest yield forecast models at F1 (flowering), F2 (siliqua formation) and F3 (siliqua development & maturity) stages for 15 districts of Assam using stepwise multiple linear regression (SMLR) and artificial neural network (ANN) techniques by analysing the yield and weather data for 27 years and to investigate the impact of weather factors in determining the yield of R&M. The results were enumerated based on coefficient of determination (R2), root mean square error (RMSE) and normalized root mean square error (RMSEn) values. ANN models were found to have greater R2 values over SMLR at all the three stages of forecast except in 2–3 districts. Similarly, profound improvement was observed in RMSE and RMSEn values of the forecast models using ANN technique. Analysing the percent error between observed and forecasted yield, ANN weather-based models were found to give more accurate pre-harvest yield prediction of R&M in the Brahmaputra valley of Assam. Temperature and relative humidity were found to be the most significant parameters in affecting R&M yield in most of the districts during all the three stages of forecast. [ABSTRACT FROM AUTHOR]

Crop yield forecasting is crucial for ensuring food security and adapting to the impacts of climate change, as it provides early insights into potential harvest outcomes and helps farmers and policymakers make informed decisions in the face of changing environmental conditions. The accuracy of the crop model–based yield forecasting frameworks is affected by the uncertainty in future weather data, which is often substituted with synthetic weather realizations generated by stochastic weather generators. This study aims to assess the performance of three recent stochastic weather generators—Global Weather Generator (GWGEN), WeatherGEN, and R Multi-Sites Autoregressive Weather GENerator (RMAWGEN) — in producing synthetic weather realizations that accurately represent regional climate variations and their impact on winter wheat yield forecasting. We utilized historical weather data from Daymet, an interpolation of daily meteorological observations that produces gridded datasets with a spatial resolution of 1 km. This data was used both as an input for the weather generators and for evaluating the performance of the generated weather realizations. Furthermore, the weather realizations generated by these weather generators across multiple winter wheat field sites in Kansas were employed in the calibrated Environmental Policy Integrated Climate (EPIC) crop model to assess the potential impact of variations in weather generators on the accuracy of crop yield forecasts. RMAWGEN and WeatherGEN excelled in accurately simulating rainy days and precipitation amounts, with WeatherGEN particularly effective in wet months and RMAWGEN performing best in dry months, showcased their proficiency in diverse weather conditions. RMAWGEN consistently showed lowest error across all variables, including precipitation, solar radiation, and both maximum and minimum temperatures. Except for GWGEN, both RMAWGEN and WeatherGEN demonstrate good agreement with Daymet in replicating spatial variability patterns. RMAWGEN notably outperformed other weather generators, particularly during the forecasting period. Consequently, it showed superior capabilities in forecasting crop yields closely matching the simulated results with Daymet data. The findings of this study are crucial for selecting accurate weather data estimates for crop yield forecasting. Utilizing alternative sources such as ensembles of multiple weather generators or outputs from sub-seasonal multi-model forecast systems may further enhance the accuracy of crop yield forecasts. [Display omitted] • Evaluated the ability of three distant weather generators to produce weather realizations accurately representing historical regional climate patterns. • Assessed the impact of variations in weather generators on the prediction skill of EPIC crop model-based winter wheat yield forecasts at field scale. • Overall, RMAWGEN demonstrated higher performance to produce more accurate weather realizations and represented regional historical climate patterns. • EPIC simulations with RMAWGEN-based synthetic weather showed potential in forecasting winter wheat yields at field scale with acceptable accuracy. [ABSTRACT FROM AUTHOR]

• Strawberry yield distribution is characterized by multiple waves. • Strawberry yield waves can be described by a Gaussian distribution model. • Gaussian distribution estimates the yield, timing, and duration of each yield wave. Strawberries (Fragaria × ananassa Duch.) are highly perishable and require intensive labor inputs for harvesting. Therefore, yield forecasting is critical for improving labor management and marketing decision-making in strawberry production. In Florida, United States, strawberry yields during winter months have a unique distribution pattern characterized by multiple waves. We hypothesized that individual yield waves can be described using Gaussian distribution, a model that represents a symmetrical bell-shaped curve. Two short-day cultivars ('Florida Radiance' and 'Florida Brilliance') and one day-neutral cultivar ('Florida Beauty') were grown in west-central Florida. Harvesting was performed 30 times, generally twice a week from November through February. Yield data were converted to weekly values prior to model fitting. The first two yield waves were described by a bimodal Gaussian distribution model, which was then converted into two unimodal Gaussian distribution models. The goodness of fit was very high (R 2 = 0.934–0.959) for both yield waves in all tested cultivars. Different yield distribution patterns of the tested cultivars were characterized quantitatively by estimating not only the yield but also the timing and duration of each yield wave. Our modeling approach provides insights into understanding cultivar-dependent fruiting phenology, yielding capacity, and fruit earliness. Such information can help optimize yield distribution through breeding and reduce yield gaps by using different cultivars or staggered planting dates. The model developed here only applies to the first two waves of fruit production. Future research will aim to model the following yield waves to fully characterize the strawberry yield distribution. [ABSTRACT FROM AUTHOR]

Yield forecasting is of immeasurable value in modern viticulture to optimize harvest scheduling and quality management. Traditionally, this task is carried out through manual and destructive sampling of production components and their accurate assessment is expensive, time-consuming, and error-prone, resulting in erroneous projections. The number of inflorescences and flowers per vine is one of the main components and serves as an early predictor. The adoption of new non-invasive technologies can automate this task and drive viticulture yield forecasting to higher levels of accuracy. In this study, different Single Stage Instance Segmentation models from the state-of-the-art You Only Look Once (YOLO) family, such as YOLOv5 and YOLOv8, were benchmarked on a dataset of RGB images for grapevine inflorescence detection and segmentation, with the aim of validating and subsequently implementing the solution for counting the number of inflorescences and flowers. All models obtained promising results, with the YOLOv8s and the YOLOv5s models standing out with an F1-Score of 95.1% and 97.7% for the detection and segmentation tasks, respectively. Moreover, the low inference times obtained demonstrate the models’ ability to be deployed in real-time applications, allowing for non-destructive predictions in uncontrolled environments.

Predicting crop yields is one of the most challenging tasks in agriculture. It plays an essential role in decision making at global, regional, and field levels. Soil, meteorological, environmental, and crop parameters are used to predict crop yield. A wide variety of decision support models are used to extract significant crop features for prediction. In precision agriculture, monitoring (sensing technologies), management information systems, variable rate technologies, and responses to inter- and intravariability in cropping systems are all important. The benefits of precision agriculture involve increasing crop yield and crop quality, while reducing the environmental impact. Simulations of crop yield help to understand the cumulative effects of water and nutrient deficiencies, pests, diseases, and other field conditions during the growing season. Farm and in situ observations (Internet of Things databases from sensors) together with existing databases provide the opportunity to both predict yields using "simpler" statistical methods or decision support systems that are already used as an extension, and also enable the potential use of artificial intelligence. In contrast, big data databases created using precision management tools and data collection capabilities are able to handle many parameters indefinitely in time and space, i.e., they can be used for the analysis of meteorology, technology, and soils, including characterizing different plant species. [ABSTRACT FROM AUTHOR]

The need of the creation of information system with specialized services which allow scientists and specialists to perform thematic processing of Earth remote sensing data, changing the data processing parameters in a certain way, and independently analyze the information received is shown.To achieve the goal of rapid provision of information, the development of specialized information system is considered on the example of the creation of the software package for the dissemination of operational space information, as well as a software package for predicting the yield of grain crops.The structure of the software package for the dissemination of operational space information is shown. The technical and functional characteristics of the separate components of the package are given. The relations of the subsystems of the package are shown during data receiving, processing, analyzing and providing information to interested specialists and researchers. Attention is drawn to the possibilities of wide application of the software package for the dissemination of operational space information for solving scientific and applied problems in various fields of knowledge.The practical application of vegetation indexes in the analysis of operational space information is shown. The data of the practical results of forecasting of the grain crops development, as well as the quantitative indicators of satellites sessions are presented. The possibility of further improvement and development of the created information system is shown.

The article provides an overview of the accuracy of various yield forecasting algorithms and offers a detailed explanation of the models and machine learning algorithms that are required for crop yield forecasting. A unified crop yield forecasting methodology is developed, which can be adjusted by adding new indicators and extensions. The proposed methodology is based on remote sensing data taken from free sources. Experiments were carried out on crops of cereals, legumes, oilseeds and forage crops in eastern Kazakhstan. Data on agricultural lands of the experimental farms were obtained using processed images from Sentinel-2 and Landsat-8 satellites (EO Browser) for the period of 2017–2022. In total, a dataset of 1600 indicators was collected with NDVI and MSAVI indices recorded at a frequency of once a week. Based on the results of this work, it is found that yields can be predicted from NDVI vegetation index data and meteorological data on average temperature, surface soil moisture and wind speed. A machine learning programming language can calculate the relationship between these indicators and build a neural network that predicts yield. The neural network produces predictions based on the constructed data weights, which are corrected using activation function algorithms. As a result of the research, the functions with the highest prediction accuracy during vegetative development for all crops presented in this paper are multi-layer perceptron, with a prediction accuracy of 66% to 99% (85% on average), and polynomial regression, with a prediction accuracy of 63% to 98% (82% on average). Thus, it is shown that the use of machine learning and neural networks for crop yield prediction has advantages over other mathematical modelling techniques. The use of machine learning (neural network) technologies makes it possible to predict crop yields on the basis of relevant data. The individual approach of machine learning to each crop allows for the determination of the optimal learning algorithms to obtain accurate predictions.

Copyright of Eastern-European Journal of Enterprise Technologies is the property of PC TECHNOLOGY CENTER and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Remote sensing-based crop yield estimation methods rely on vegetation indices, which depend on the availability of the number of observations during the year, influencing the value of the derived crop yield. In the present study, a robust yield estimation method was improved for estimating the yield of corn, winter wheat, sunflower, and rapeseed in Hungary for the period 2000–2020 using 16 vegetation indices. Then, meteorological data were used to reduce the differences between the estimated and census yield data. In the case of corn, the best result was obtained using the Green Atmospherically Resistant Vegetation Index, where the correlation between estimated and census data was R2 = 0.888 before and R2 = 0.968 after the meteorological correction. In the case of winter wheat, the Difference Vegetation Index produced the best result with R2 = 0.815 and 0.894 before and after the meteorological correction. For sunflower, these correlation values were 0.730 and 0.880, and for rapeseed, 0.765 and 0.922, respectively. Using the meteorological correction, the average percentage differences between estimated and census data decreased from 7.7% to 3.9%, from 6.7% to 3.9%, from 7.2% to 4.2%, and from 7.8% to 5.1% in the case of corn, winter wheat, sunflower, and rapeseed, respectively. [ABSTRACT FROM AUTHOR]

The possibility is considered of using data of the Sentinel-1B radar satellite in agriculture, in particular, for the crop monitoring and grain crop yield forecasting. For this purpose, based on satellite data, the Radar Vegetation Index RVI was calculated. The values of RVI obviously indicate the dynamics of the development of such crops as spring wheat, oat, and barley. The correlation and regression analysis of the relationship between the normalized difference vegetation index NDVI and RVI revealed the presence of a significant dependence between the indices. The normalized radar vegetation index NRVI was calculated to use radar data in predicting the expected yield. As a part of the experiment, yield forecasts at the farm in the Kochenevo district (the Novosibirsk region) for the 2018 and 2019 growing seasons were calculated. The calculation results showed the yield forecast accuracy above 90%, which allowed the use of NRVI in the 2020 operational activities. [ABSTRACT FROM AUTHOR]

Dust accumulation on the photovoltaic system adversely degrades its power conversion efficiency (PCE). Focusing on residential installations, dust accumulation on PV modules installed in tropical regions may be vulnerable due to lower inclination angles and rainfall that encourage dust settlement on PV surfaces. However, most related studies in the tropics are concerned with studies in the laboratory, where dust collection is not from the actual field, and an accurate performance prediction model is impossible to obtain. This paper investigates the dust-related degradation in the PV output performance based on the developed Artificial Neural Network (ANN) predictive model. For this purpose, two identical monocrystalline modules of 120 Wp were tested and assessed under real operating conditions in Melaka, Malaysia (2.1896° N, 102.2501° E), of which one module was dust-free (clean). At the same time, the other was left uncleaned (dusty) for one month. The experimental datasets were divided into three sets: the first set was used for training and testing purposes, while the second and third, namely Data 2 and Data 3, were used for validating the proposed ANN model. The accuracy study shows that the predicted data using the ANN model and the experimentally acquired data are in good agreement, with MAE and RMSE for the cleaned PV module are as low as 1.28 °C, and 1.96 °C respectively for Data 2 and 3.93 °C and 4.92 °C respectively for Data 3. Meanwhile, the RMSE and MAE for the dusty PV module are 1.53°C and 2.82 °C respectively for Data 2 and 4.13 °C and 5.26 °C for Data 3. The ANN predictive model was then used for yield forecasting in a residential installation and found that the clean PV system provides a 7.29 % higher yield than a dusty system. The proposed ANN model is beneficial for PV system installers to assess and anticipate the impacts of dust on the PV installation in cities with similar climatic conditions. [ABSTRACT FROM AUTHOR]

Manual yield estimation usually requires a lot of work and is expensive. With the help of modern image recognition systems, it is already possible to create yield forecasts to determine area-related yield capacity and fruit size distribution. This makes it possible to apply cultivation measures in a more targeted way and to optimize storage and logistics. Therefore, in this paper, five different commercially available systems were tested for their precision and practicality with different varieties and at different locatins. For this purpose, the data obtained were compared with manually determined data and the deviation was calculated. It was found that there were large differences between the various systems, although some systems already showed sufficient accuracy. Most of the systems, however, had too much deviation and the time required to collect the data was often higher than that required for manual measurement.

Early forecasting of crop yield from field to region is important for stabilizing markets and safeguarding food security. Producing a precise forecasting result with fewer inputs is an ongoing goal for the large-area yield evaluation. We present one approach of yield prediction for maize that was explored by incorporating remote-sensing-derived land surface temperature (LST) and field in-season data into a series of logistic models with only a few parameters. Continuous observation data of maize were utilized to calibrate and validate the corresponding logistic models for regional biomass estimating based on field temperatures (including crop canopy temperature (Tc)) and relative dry/fresh biomass accumulation. The LST maps from MOD11A1 products, which are considered to be matched as Tc in large irrigation districts, were assimilated into the validated models to estimate the biomass accumulation. It was found that the temporal-scale difference between the instantaneous LST and the daily average value of field-measured Tc was eliminated by data normalization method, indicating that the normalized LST could be input directly into the model as an approximation of the normalized Tc. Making one observed biomass in-season as the driving force, the maximum of dry/fresh biomass accumulation (DBA/FBA) at harvest could be estimated. Then, grain yield forecasting could be achieved according to the local harvest index of maize. Silage and grain yields were evaluated reasonably well compared with field observations based on the regional map of LST values obtained in 2017 in Changchun, Jilin Province, China. Here, satisfactory grain and silage yield forecasting was provided by assimilating once measured value of DBA/FBA at the middle growth period (early August) into the model in advance of harvest. Meanwhile, good results were obtained in the application of this approach using field data in 2016 to predict grain yield ahead of harvest in the Jiefangzha sub-irrigation district, Inner Mongolia, China. This study demonstrated that maize yield can be forecasted accurately prior to harvest by assimilating remote-sensing-derived LST and field data into the logistic models at a regional scale considering the spatio-temporal scale extension of ground information and crop dynamic growth in real time.

Subseasonal-to-seasonal (S2S) prediction of winter wheat yields is crucial for farmers and decision-makers to reduce yield losses and ensure food security. Recently, numerous researchers have utilized machine learning (ML) methods to predict crop yield, using observational climate variables and satellite data. Meanwhile, some studies also illustrated the potential of state-of-the-art dynamical atmospheric prediction in crop yield forecasting. However, the potential of coupling both methods has not been fully explored. Herein, we aimed to establish a skilled ML–dynamical hybrid model for crop yield forecasting (MHCF v1.0), which hybridizes ML and a global dynamical atmospheric prediction system, and applied it to northern China at the S2S time scale. In this study, we adopted three mainstream machining learning algorithms (XGBoost, RF, and SVR) and the multiple linear regression (MLR) model, and three major datasets, including satellite data from MOD13C1, observational climate data from CRU, and S2S atmospheric prediction data from IAP CAS, used to predict winter wheat yield from 2005 to 2014, at the grid level. We found that, among the four models examined in this work, XGBoost reached the highest skill with the S2S prediction as inputs, scoring R2 of 0.85 and RMSE of 0.78 t/ha 3–4 months, leading the winter wheat harvest. Moreover, the results demonstrated that crop yield forecasting with S2S dynamical predictions generally outperforms that with observational climate data. Our findings highlighted that the coupling of ML and S2S dynamical atmospheric prediction provided a useful tool for yield forecasting, which could guide agricultural practices, policy-making and agricultural insurance. [ABSTRACT FROM AUTHOR]

Com, which has an important place among agricultural products, has many uses, from animal feed to com syrup in processed foods, to different uses in basic foods. The high demand level that arises with the increase in industrial use as well as the use of feed due to increased animal production ensures that production remains at these levels.<;ukurova region is one of the important agricultural areas of Turkey, and many plants of economic importance are produced. 15% of com production in Turkey is made in Adana. In the study, the second crop com in the Akarsu region was monitored with LANDSAT 8 satellite image and the relationship of total product data with NDVI values was studied.According to the 201 7 Correlation result there is a linear corelation between minimum reflection values and yield. Correlation coefficient is 0,41 2. It cannot be said that the minimum reflection value has an effect on yield. According to the 2018 Correlation result there is a linear corelation between minimum reflection values and yield. Correlation coefficient is 0,359. It cannot be said that the minimum reflection value has an effect on yield. According to corelation result there is a linear corelation between maximum reflection values and yield. Correlation coefficient is 0,467. It cannot be said that the maximum reflection value has an effect on yield. [ABSTRACT FROM AUTHOR]

Rice is the main staple food of the country but crop productivity in some years declines due to erratic monsoon and non-uniformity in spatial and temporal distribution of rainfall. Hence, assessing productivity of the rice crop in advance using meteorological and plant physiological attributes will be helpful for planners to take decision on contingency measures. In this investigation, dry biomass of early phenophases (active tillering, panicle initiation, boot leaf stages, flowering),peak intercepted photosynthetically active radiation (IPAR), peak spectral reflectance based vegetation indices of 3 rice varieties under 3 nitrogen levels (50, 100 and 130 kg ha-1) were made correlated with grain yield.Based on interrelationship it was found that biomass of flowering period was better correlated with grain yield with the R2 value of 0.75.Inter-relationship between peak IPAR(%), remotely sensed peak simple ratio index (IR/R) and normalized difference vegetation index (NDVI)with the rice yield were also established. Multiple regression modelwas developed by interrelating yield as dependant variable with dry biomass of flowering stage, peak IPAR(%) and peak IR/R and NDVI as independent variables which may be used as an effective tool for early prediction of rice yield, at least 30-40 days in advance. The grain yield was also estimated through developed algorithm using MODIS satellite derived NDVI and compared with that of actual yield.

Mathematical models have been widely employed for the simulation of growth dynamics of annual crops, thereby performing yield prediction, but not for fruit tree species such as jujube tree (Zizyphus jujuba). The objectives of this study were to investigate the potential use of a modified WOFOST model for predicting jujube yield by introducing tree age as a key parameter. The model was established using data collected from dedicated field experiments performed in 2016–2018. Simulated growth dynamics of dry weights of leaves, stems, fruits, total biomass and leaf area index (LAI) agreed well with measured values, showing root mean square error (RMSE) values of 0.143, 0.333, 0.366, 0.624 t ha−1 and 0.19, and R2 values of 0.947, 0.976, 0.985, 0.986 and 0.95, respectively. Simulated phenological development stages for emergence, anthesis and maturity were 2, 3 and 3 days earlier than the observed values, respectively. In addition, in order to predict the yields of trees with different ages, the weight of new organs (initial buds and roots) in each growing season was introduced as the initial total dry weight (TDWI), which was calculated as averaged, fitted and optimized values of trees with the same age. The results showed the evolution of the simulated LAI and yields profiled in response to the changes in TDWI. The modelling performance was significantly improved when it considered TDWI integrated with tree age, showing good global (R2≥0.856, RMSE≤0.68 t ha−1) and local accuracies (mean R2≥0.43, RMSE≤0.70 t ha−1). Furthermore, the optimized TDWI exhibited the highest precision, with globally validated R2 of 0.891 and RMSE of 0.591 t ha−1, and local mean R2 of 0.57 and RMSE of 0.66 t ha−1, respectively. The proposed model was not only verified with the confidence to accurately predict yields of jujube, but it can also provide a fundamental strategy for simulating the growth of other fruit trees.

Remote sensing methods based on UAV and hand-held devices as well have been used to assess the response to nitrogen and sulfur fertilization of hypoallergenic genotypes of winter wheat. The field experiment was conducted using the split-split-plot design with three repetitions. The first factor was the two genotypes of winter wheat specified as V1 (without allergic protein) and V2 (with allergic protein), and the second factor was three doses of sulfur fertilization: 0, 20 and 40 kg S per ha. The third factor consisted of six doses of nitrogen fertilization: 0, 40, 60, 80, 100 and 120 kg N·ha−1. Monitoring the values of the indicators depending on the level of nitrogen and sulfur fertilization allowed the results to be used in yield forecasting, assessment of plant condition, LAI value, nutritional status in the cultivation of wheat. The maximum yield should be expected at doses of 94 and 101 kg N ha−1 for genotypes V1 and V2, respectively, giving yields of 5.39 and 4.71 Mg ha−1. On the basis of the tested vegetation indices, the highest doses of N should be applied using the normalized difference RedEdge (NDRE), and the lowest ones based on the enhanced vegetation index (EVI), and, in the latter case, a reduction in yield of more than 200 kg ha−1 in the V2 genotype should be taken into account.

Predicting crop yields is one of the most challenging tasks in agriculture. It plays an essential role in decision making at global, regional, and field levels. Soil, meteorological, environmental, and crop parameters are used to predict crop yield. A wide variety of decision support models are used to extract significant crop features for prediction. In precision agriculture, monitoring (sensing technologies), management information systems, variable rate technologies, and responses to inter- and intravariability in cropping systems are all important. The benefits of precision agriculture involve increasing crop yield and crop quality, while reducing the environmental impact. Simulations of crop yield help to understand the cumulative effects of water and nutrient deficiencies, pests, diseases, and other field conditions during the growing season. Farm and in situ observations (Internet of Things databases from sensors) together with existing databases provide the opportunity to both predict yields using “simpler” statistical methods or decision support systems that are already used as an extension, and also enable the potential use of artificial intelligence. In contrast, big data databases created using precision management tools and data collection capabilities are able to handle many parameters indefinitely in time and space, i.e., they can be used for the analysis of meteorology, technology, and soils, including characterizing different plant species.