A robust forecast of rice yields is of great importance for medium-to-long-term planning and decision-making in cereal production, from regional to national level. Incorporation of spatially correlated adjacent effects in forecasting models in general, results in accurate forecast. The Space Time Autoregressive Moving Average (STARMA) is the most popular class of model in linear spatiotemporal time series modelling. However, STARMA cannot process nonlinear spatiotemporal relationships in datasets. Alternately, Time Delay Neural Network (TDNN) is a most popular machine learning algorithm to model the nonlinear pattern in data. To overcome these limitations, two-stage STARMA approach was developed to predict rice yield in some of the most intensive national rice agroecosystems in India. The Mean Absolute Percentage Errors value of proposed STARMA-II approach is lower compared to Autoregressive Moving Average (ARIMA) and STARMA model in all examined districts, while the Diebold-Mariano test confirmed that STARMA-II model is significantly different from classical approaches. The proposed STARMA-II approach is promising alternative to classical linear and nonlinear spatiotemporal time series models for estimating mixed linear and nonlinear patterns and can be advanced tool for mid-to-long-term sustainable planning and management of crop yields and patterns in agroecosystems, i.e., food supply and demand from local to regional levels.

In agroecosystems, drought is a critical climatic phenomenon that affects evapotranspiration and induces water stress in plants. The objective in this study was to characterize and forecast water stress in the Hyderabad region of India using artificial intelligence models. The monthly precipitation data for the period 1982–2021 was characterized by the standardized precipitation index (SPI) and modeled using the classical autoregressive integrated moving average (ARIMA) model and artificial intelligence (AI), i.e., artificial neural network (ANN) and support vector regression (SVR) model. The results show that on the short-term SPI3 time scale the studied region experienced extreme water deficit in 1983, 1992, 1993, 2007, 2015, and 2018, while on the mid-term SPI6 time scale, 1983, 1991, 2011, and 2016 were extremely dry. In addition, the prediction of drought at both SPI3 and SPI6 time scales by AI models outperformed the classical ARIMA models in both, training and validation data sets. Among applied models, the SVR model performed better than other models in modeling and predicting drought (confirmed by root mean square error—RMSE), while the Diebold–Mariano test confirmed that SVR output was significantly superior. A reduction in the prediction error of SVR by 48% and 32% (vs. ARIMA), and by 21% and 26% (vs. ANN) was observed in the test data sets for both SPI3 and SPI6 time scales. These results may be due to the ability of the SVR model to account for the nonlinear and complex patterns in the input data sets against the classical linear ARIMA model. These results may contribute to more sustainable and efficient management of water resources/stress in cropping systems.

Global climate change is anticipated to have a profound impact on drought occurrences, leading to detrimental consequences for the environment, socioeconomic relations, and ecosystem services. In order to evaluate the extent of drought impact, a comprehensive study was conducted in the Hyderabad–Karnataka region, India. Precipitation data from 31 stations spanning a 50-year period (1967–2017) were analyzed using the standardized precipitation index (SPI) based on gamma distribution. The findings reveal that approximately 15% of the assessed years of experienced drought conditions, with a range of influence between 41% and 76% under SPI_3, and between 43% and 72% under SPI_6. Examining the timescale magnitude frequency provided insights into variations in the severity of drought events across different locations and timescales. Notably, the Ballari (−8.77), Chitapur (−8.22), and Aland (−7.40) regions exhibited the most significant magnitudes of drought events for SPI_3 with a 5-year return period. The heightened risk of recurrent droughts in the study area emphasizes the necessity of integrating SPI in decision-making processes, as such integration can markedly contribute to the development of reliable and sustainable long-term water management strategies at regional and national levels.

The prediction of potential evapotranspiration (PET) is quite important task for reliable management of irrigation systems. This article is generally based on the models which try to mimic the actual occurrence of the Potential evapotranspiration in the future days for a Raichur district. In this study the potential evapotranspiration was estimated with the help of max and min temperature (°C) data using a Thornthwaite method and the prediction was carried out using the seasonal Autoregressive moving average method (SARIMA). The models were developed based upon autocorrelation function (ACF) and partial autocorrelation function (PACF). Furthermore, the model with the least Akaike Information Criteria (AIC) and Bayesian Information Criteria (BIC) values were selected. The models selected for different stations were ARIMA(2,0,2)(1,1,2)₁₂, ARIMA(1,0,1)(2,1,0)₁₂, ARIMA(1,0,1)(1,1,2)₁₂ and ARIMA(1,0,1) (2,1,0)₁₂ for Riachur, Manvi, Sindhanuru and Lingasuguru respectively. Furthermore, the results showed that the models developed for Manvi and Sindhanuru were found to be quite promising compared to the other two stations. All four models were found to be producing better results up to a lead time forecast of one month. The models provided significant potential in improving the decision making in irrigation planning and command area management practices for better management of water resources.