Initial evaluations of the System of Rice Intensification in India and elsewhere focused mainly on its impacts on yield and income, and usually covered just one or two seasons. Researchers at the ICAR-Indian Institute of Rice Research have conducted a more comprehensive evaluation of SRI methods over six years (six wet and six dry seasons), comparing them with three alternatives: modified, partially mechanized SRI (MSRI) to reduce labor requirements; direct-seeded rice (DSR) as an alternative method for growing rice; and conventional transplanting of rice with flooding of fields (CTF). Grain yield with SRI methods was found to be about 50% higher than with CTF (6.35 t ha⁻¹ vs. 4.27 t ha⁻¹), while the MSRI yield was essentially the same (6.34 t ha⁻¹), 16% more than with DSR (5.45 t ha⁻¹). Water productivity with SRI methods was 5.32–6.85 kg ha-mm⁻¹, followed by 4.14–5.72 kg ha-mm⁻¹ for MSRI, 5.06–5.11 kg ha-mm⁻¹ for DSR, and 3.52–4.56 kg ha-mm⁻¹ for CTF. In comparison with CTF, SRI methods significantly enhanced soil microbial populations over time: bacteria by 12%, fungi by 8%, and actinomycetes by 20%. Biological activity in the rhizosphere was also higher as indicated by 8.5% greater dehydrogenase and 16% more FDA enzymes in soil under SRI management. Similarly, an indicator of soil organic matter, glucosidase activity, was 78% higher compared to CTF. SRI enhanced the relative abundance of beneficial microbial-feeding nematodes by 7.5% compared to CTF, while that of plant-pathogenic nematodes was 7.5% lower under SRI. Relative to conventional methods, SRI management reduced GHG emissions by 21%, while DSR reduced them by 23%, and MSRI by 13%, compared to standard rice-growing practice. Economic analysis showed both gross and net economic returns to be higher with SRI than with the other management systems evaluated. While the six-year study documented many advantages of SRI crop management, it also showed that MSRI is a promising adaptation that provides similar benefits but with lower labor requirements.

Temperature plays a crucial role in influencing the growth and development of crops. Rice, being a significant cereal crop, is highly sensitive to both low and high temperature stresses. Upcoming season temperature forecasts help in site-specific crop management, such as assessing crop growth, pest outbreaks, and suggesting heat-tolerant varieties and prediction models. This paper focuses on the prediction of temperatures using a combination of GIS and machine learning models. The study involved in the estimation of daily maximum temperatures for India, by utilizing the Random Forest algorithm within a machine learning model. The training and testing dataset encompassed Indian Meteorological Department (IMD) grid-based daily temperature data (307 grid points across 365 days) from 2010 to 2019. In contrast, the data for 2020 was reserved as a validation dataset. Since the daily temperature data is available for only 307 grid points and there are more than 700 districts in India, GIS tool has been used for estimating temperatures at unknown points using spatial interpolation method. QGIS software was employed to handle the spatial interpolation of grid-based data using Thiessen polygons. The model's performance was evaluated using the R-squared (R²) values, which ranged between 0.8 and 0.9, indicating a strong and accurate performance of the model. The model performed particularly well when comparing the predicted temperature values for 2020 with the validation dataset, as evidenced by a correlation coefficient (r²) of 0.88. Furthermore, it demonstrates that machine learning algorithms, combined with GIS models, are capable of spatial temperature prediction when forecasting large-scale temperature patterns across India. The ability to continually update the training data with real-time IMD information enhances self-learning modules and results in more accurate temperature predictions enabling the timely generation site-specific crop management advisories.

Initial evaluations of the System of Rice Intensification in India and elsewhere have mainly fo-cused on its impact on yield and income and have usually covered just one or two seasons. Re-searchers at the ICAR-Indian Institute of Rice Research conducted a more comprehensive evalua-tion of SRI methods over six years (six wet and six dry seasons), comparing these methods with three other rice crop management systems: modified, partially mechanized SRI (MSRI); direct-seeded rice (DSR); and normal transplanting with inundated fields (NTP). SRI grain yield was found to be about 50% higher than with NTP (6.35 t ha-1 vs 4.27 t ha-1), while the MSRI yield was essentially the same (6.34 t ha-1) and 16% higher than with DSR (5.45 t ha-1). Compared to NTP, SRI methods significantly enhanced soil microbial populations over time, bacteria by 12%, fungi by 8%, and actinomycetes by 20%. Indicators of biological activity in the rhizosphere were also higher, dehydrogenase by 8.5% and FDA enzymes by 16%. Glucosidase activity, an indicator of soil organic matter, was 78% higher. Relative to normal transplanting methods, SRI reduced GHG emissions by 21%, while DSR reduced them by 23% and MSRI by 13%, which indicated pos-itive effects of the alternate and improved methods over normal transplanting. Economic analy-sis showed that both gross and net economic returns to be higher with SRI than with MSRI and the other management systems evaluated. While the six-year study documented many ad-vantages of SRI crop management, the MSRI version evaluated is a promising adaptation that provide similar benefits but with lower labor requirements.