Explore the vast range of titles available.

Rice is generally grown under completely flooded condition and providing food for more than half of the world’s population. Any changes in weather parameters might affect the rice productivity thereby impacting the food security of burgeoning population. So, the crop yield forecasting based on weather parameters will help farmers, policy makers and administrators to manage adversities. The present investigation examines the application of stepwise multiple linear regression (SMLR), artificial neural network (ANN) solely and in combination with principal components analysis (PCA) and penalised regression models (e.g. least absolute shrinkage and selection operator (LASSO) or elastic net (ENET)) for rice yield prediction using long-term weather data. The R2 and root mean square error (RMSE) of the models varied between 0.22–0.98 and 24.02–607.29 kg ha−1, respectively during calibration. During validation with independent dataset, the RMSE and normalised root mean square error (nRMSE) ranged between 21.35–981.89 kg ha−1 and 0.98–36.7%, respectively. For evaluation of multiple models for multiple locations statistically, overall average ranks on the basis of R2 and RMSE of calibration; RMSE and nRMSE of validation were calculated and non-parametric Friedman test was applied to check the significant difference among the models. The ranking of the models revealed that LASSO (2.63) was the best performing model followed by ENET (3.07) while PCA-ANN (4.19) was the worst model which was found significant at p < 0.001. The reason behind good performance of LASSO and ENET is that these models prevent overfitting and reduce model complexity by penalising the magnitude of coefficients. Then, pairwise multiple comparison test was performed which indicated LASSO as the best model which was found similar to SMLR and ENET. So, for prediction of rice yield, these models can very well be utilised for west coast of India.

Accurate crop yield forecasting prior to harvest plays a vital role in formulating, implementing, and optimizing policies concerning food safety, as well as in the efficient management of agro-product storage and marketing. The growth and development of crops are inherently influenced by weather conditions, making models that utilize weather variables indispensable for providing reliable predictions of crop yields. However, selecting the most suitable crop production forecasting model can pose a challenging task. Therefore, in this study, three multivariate models were developed to predict soybean yield in eight major districts of Uttarakhand: Udham Singh Nagar, Almora, Uttarkashi, Dehradun, Pauri-Garhwal, Tehri-Garhwal, Rudraprayag, and Pithoragarh. The models used were Artificial Neural Networks (ANN), Principal Component Analysis—Artificial Neural Networks (PCA-ANN), and Least Absolute Shrinkage and Selection Operator (LASSO). To build and assess the models, historical time series data of soybean yields and weather indices were utilized. The dataset was divided into calibration (80% of the data) and validation sets (remaining data) to evaluate the model predictions. The models were trained to predict soybean yield based on average values of phenological stages derived from daily weather data. Both weighted and unweighted weather indices were employed in the computation. After evaluating the models, it was observed that the PCA-ANN model outperformed all others in predicting soybean yield. The overall ranking of model performances for all locations was as follows: PCA-ANN > ANN > LASSO. It was also noted that the PCA-ANN hybrid model was the most effective for forecasting soybean yields in the examined districts of Uttarakhand, providing valuable insights for agricultural planning and decision-making.

Pre-harvest yield forecasting is important for the sustainability of agricultural companies, enabling more sustainable economic decision-making. In the present study, we propose an approach based on the sum of degree days of the corn crop related to the dates of satellite images to organize the data of two crops generating predictive models with the k-nearest neighbors (KNN) and extreme gradient boosting (XGBoost). The field study was carried out in a commercial area during the 2017/18 and 2018/19 harvests. Spectral data were obtained from Sentinel-2 satellite images. After the correction and processing of the images, the values ​​of the spectral bands and the vegetation indices were obtained. For the development of the models, the images obtained throughout the cycle were divided into three classes of the mean weeks before harvest (WBH) from different degree-days (GD) during the cycle, in this study we adopted 12 combinations of data inputs to develop the models. In yield forecasting, we were able to forecast approximately 30 to 70 days before harvest (500 to 900 degree-days before harvest), in addition, the most accurate models were when the data used as driven variables were the spectral bands of the red, blue, green and nir collected from 800 to 1200 degree-days of the culture (WBH4). For the models developed, combined with WBH for yield forecast, it was possible to forecast yield with an average error of 0.503 t ha-1, and the greatest precision and accuracy occurred with the use of all variables RGB e Near-infrared.

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.

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.

Climate change and extreme weather events pose challenges to food security, emphasizing the need for reliable and timely monitoring of crop and rangeland conditions. For this purpose, long-term consistent Earth Observation datasets on vegetation conditions are typically used in early warning and crop yield forecast systems. However, the near-real-time (NRT) production of high quality datasets and the need to guarantee long-term records present various challenges. To address these, we present a NRT global dataset of Fraction of Photosynthetically Active Radiation (FPAR) at 500 m resolution, optimized for agricultural applications. Our dataset combines MODIS-FPAR (Collection 6.1) and VIIRS-FPAR (Collection 2) data, ensuring continuity from 2000 to well beyond 2030. We applied a robust filtering approach based on the Whittaker smoother to produce reliable FPAR estimates in NRT, accounting for sparse and irregular spaced observations due to cloud cover. The dataset is composed of two 10 d filtered timeseries: (1) MODIS-FPAR for 2000 to 2023, being the reference dataset, and (2) intercalibrated VIIRS-FPAR for 2018 onward. While several methods can effectively smooth and gap-fill FPAR data (i.e., using observations before and after the estimation date), our method is designed for optimal filtering in NRT (i.e., using only prior observations). Our approach yields six successive estimates of the same FPAR data point with increasing quality: an inital estimate immediately after the 10 d reference period, four subsequent estimates every 10 d using new observations, and a final consolidated estimate 90 d later. The implemented filtering ingests the available FPAR observations and their original quality assessment (QA) layers. To avoid unrealistic extrapolation when observations are sparse, we impose constraints, season and location specific, to FPAR estimates. We then intercalibrated the VIIRS-FPAR with the MODIS-FPAR filtered timeseries, using a mean difference correction approach, to ensure consistency between both series. This paper describes the filtering and intercalibration method used, the quality assessment of resulting timeseries, and details the obtained products and the corresponding QA layers. The NRT FPAR dataset is publicly available through the Joint Research Centre Data Catalogue, https://doi.org/10.2905/1aac79d8-0d68-4f1c-a40f-b6e362264e50 (Seguini et al., 2025).

Rice is one of the most important cereal foods not only for India but also for the world. The production of crop depends upon the favorable climatic conditions. Farmers’ access to more accurate data on crop yields in various climate conditions can aid in crucial agronomic and crop selection decisions. Taking this into account, the motive of the present research was to find the best method of predicting rice crop yield in seven important rice producing districts of Uttarakhand, namely Udham Singh Nagar, Nainital, Haridwar, Dehradun, Champawat, Tehri-Garhwal, and Pauri Garhwal. Data on the weather variables for the crop-growing season (27th to 44th SMW) for 19 years was gathered from the respective district and the NASA power website, while rice production data for the research period was gathered from the Directorate of Economics and Statistics, Ministry of Agriculture and Farmers Welfare. Stepwise multiple linear regression (SMLR), least absolute shrinkage and selection operator (LASSO), ridge regression, elastic net (ELNET), and artificial neural network (ANN) were employed for the model’s development. The 80% data of the total datasets was utilized to calibrate the models, while the remaining 20% data was allocated for the model validation. On examining these models, LASSO was found to be the finest performing model followed by ELNET, while SMLR was the worst performing model during calibration stage. During validation stage, ANN performed better for Champawat, Dehradun, Haridwar, Pauri Garhwal, and Udham Singh Nagar. The performance of ELENT and LASSO was found to be best for Nainital and Tehri Garhwal, respectively. The performance of ridge regression and SMLR were found to be poor as compared to the other models for the rice yield forecasting.

The prediction of crop yield before harvest is crucial for facilitating the formulation and implementation of policies about food safety, transportation cost, and import-export, storage and marketing of agro-products. The weather plays a crucial role in crop growth and development. Therefore, models using weather variables can provide reliable forecasts for crop yield and choosing the right model for crop production forecasts can be difficult. Therefore in the present study, an attempt was made to find the best model for wheat yield forecast by using five different techniques viz. Stepwise Multiple Linear Regression (SMLR), Artificial Neural Network (ANN), Least Absolute Shrinkage and Selection Operator (LASSO), Elastic Net (ELNET) and Ridge regression. Historical wheat yield data (taken from the Directorate of Economics and Statistics, Ministry of Agriculture and Farmers Welfare) and weather data of past 18-20 years were collected for seven different districts of Uttarakhand. Analysis was carried out by fixing 80% of the data for calibration and remaining dataset for validation. The present study concluded that the performance of ANN was good for crop yield forecasting as compared to the other models based on the value of RMSE (0.005 - 0.474) and nRMSE (0.166 - 26.171).

Soil moisture (SM) is a key variable of the regional hydrological cycle and has important applications for water resource and agricultural drought management. Various global soil moisture products have been mostly retrieved from microwave remote sensing data. However, currently there is rarely spatially explicit and time-continuous soil moisture information with a high resolution at the national scale. In this study, we generated a 1 km soil moisture dataset for dryland wheat and maize in China (ChinaCropSM1 km) over 1993–2018 through a random forest (RF) algorithm based on numerous in situ daily observations of soil moisture. We independently used in situ observations (181 327 samples) from the agricultural meteorological stations (AMSs) across China for training (164 202 samples) and others for testing (17 125 samples). An irrigation module was first developed according to crop type (i.e., wheat, maize), soil depth (0–10, 10–20 cm) and phenology. We produced four daily datasets separately by crop type and soil depth, and their accuracies were all satisfactory (wheat r 0.93, ubRMSE 0.033 m3 m−3; maize r 0.93, ubRMSE 0.035 m3 m−3). The spatiotemporal resolutions and accuracy of ChinaCropSM1 km were significantly better than those of global soil moisture products (e.g., r increased by 116 %, ubRMSE decreased by 64 %), including the global remote-sensing-based surface soil moisture dataset (RSSSM) and the European Space Agency (ESA) Climate Change Initiative (CCI) SM. The approach developed in our study could be applied to other regions and crops in the world, and our improved datasets are very valuable for many studies and field management, such as agricultural drought monitoring and crop yield forecasting. The data are published in Zenodo at https://doi.org/10.5281/zenodo.6834530 (wheat0–10) (Cheng et al., 2022a), https://doi.org/10.5281/zenodo.6822591 (wheat10–20) (Cheng et al., 2022b), https://doi/org/10.5281/zenodo.6822581 (maize0–10) (Cheng et al., 2022c) and https://doi.org/10.5281/zenodo.6820166 (maize10–20) (Cheng et al., 2022d).