Securing China's rice harvest: unveiling dominant factors in production using multi-source data and hybrid machine learning models.

Ensuring the security of China's rice harvest is imperative for sustainable food production. The existing study addresses a critical need by employing a comprehensive approach that integrates multi-source data, including climate, remote sensing, soil properties and agricultural statistics from 2000 to 2017. The research evaluates six artificial intelligence (AI) models including machine learning (ML), deep learning (DL) models and their hybridization to predict rice production across China, particularly focusing on the main rice cultivation areas. These models were random forest (RF), extreme gradient boosting (XGB), conventional neural network (CNN) and long short-term memory (LSTM), and the hybridization of RF with XGB and CNN with LSTM based on eleven combinations (scenarios) of input variables. The main results identify that hybrid models have performed better than single models. As well, the best scenario was recorded in scenarios 8 (soil variables and sown area) and 11 (all variables) based on the RF-XGB by decreasing the root mean square error (RMSE) by 38% and 31% respectively. Further, in both scenarios, RF-XGB generated a high correlation coefficient (R2) of 0.97 in comparison with other developed models. Moreover, the soil properties contribute as the predominant factors influencing rice production, exerting an 87% and 53% impact in east and southeast China, respectively. Additionally, it observes a yearly increase of 0.16 °C and 0.19 °C in maximum and minimum temperatures (Tmax and Tmin), coupled with a 20 mm/year decrease in precipitation decline a 2.23% reduction in rice production as average during the study period in southeast China region. This research provides valuable insights into the dynamic interplay of environmental factors affecting China's rice production, informing strategic measures to enhance food security in the face of evolving climatic conditions.

Prediction of irrigation groundwater quality parameters using ANN, LSTM, and MLR models.

Forecasting the irrigation groundwater parameters helps plan irrigation water and crop, and it is commonly expensive because it needs various parameters, mainly in developing nations. Therefore, the present research's core objective is to create accurate and reliable machine learning models for irrigation parameters. To accomplish this determination, three machine learning (ML) models, viz. long short-term memory (LSTM), multi-linear regression (MLR), and artificial neural network (ANN), have been trained. It is validated with mean squared error (MSE) and correlation coefficients (r), root mean square error (RMSE), and mean absolute error (MAE). These machine learning models have been used and applied for predicating the six irrigation water quality parameters such as sodium absorption ratio (SAR), percentage of sodium (%Na), residual sodium carbonate (RSC), magnesium hazard (MH), Permeability Index (PI), and Kelly ratio (KR). Therefore, the two scenario performances of ANN, LSTM, and MLR have been developed for each model to predict irrigation water quality parameters. The first and second scenario performance was created based on all and second reduction input variables. The ANN, LSTM, and MLR models have discovered that excluding for ANN and MLR models shows high accuracy in first and second scenario models, respectively. These model's accuracy was checked based on the mean squared error (MSE), correlation coefficients (r), and root mean square error (RMSE) for training and testing processes serially. The RSC values are highly accurate predicated values using ANN and MLR models. As a result, machine learning models may improve irrigation water quality parameters, and such types of results are essential to farmers and crop planning in various irrigation processes.

Applications of various data-driven models for the prediction of groundwater quality index in the Akot basin, Maharashtra, India.

Data-driven models are important to predict groundwater quality which is controlling human health. The water quality index (WQI) has been developed based on the physicochemical parameters of water samples. In this area, water quality is medium to poor and is found in saline zones; very high pH ranges are directly affected on the water quality in this study area. Conventional WQI computation demands more time and is often observed with enormous errors during the calculation of sub-indices. In the present work, four standalone methods such as additive regression (AR), M5P tree model (M5P), random subspace (RSS), and support vector machine (SVM) were employed to predict WQI based on variable elimination technique. The groundwater samples were collected from the Akot basin area, located in the Akola district, Maharashtra, in India. A total of nine different input combinations were developed in this study. The datasets were demarcated into two classes (ratio 80:20) for model construction (training dataset) and model verification (testing dataset) using a fivefold cross-validation approach. The models were assessed using statistical and graphical appraisal metrics. The best input combinations varied among the model, generally, the optimal input variables (EC, pH, TDS, Ca, Mg, and Cl) during the training and validation stages. Results show that AR outperformed the other data-driven models (R2 = 0.9993, MAE = 0.5243, RMSE = 0.0.6356, %RAE = 3.8449, and RRSE% = 3.9925). The AR is proposed as an ideal model with satisfactory results due to enhanced prediction precision with the minimum number of input parameters and can thus act as the reliable and precise method in the prediction of WQI at the Akot basin.