No abstract

With the development of large‐scale rice cultivation management initiatives in East Asia, there is concern that a reduction in the number of human cultivators per unit area may lead to poor water management, which could result in decreased land productivity, owing to abnormally high‐ and low‐temperature damage to crops. Accurate simulation of paddy field water temperature is important for studying its impact on crops and providing timely information to aid in decision‐making for more efficient management under limited resources. We propose a neural‐network framework that considers the heat transfer by the vegetation canopy and applies physical‐theory constraints in its training. A novel tuning method is proposed to cope with the trade‐off between water temperature accuracy and physical consistency during training to ensure that the calculated water temperature variations in a paddy field enjoy high accuracy and physical consistency. In the experiments, the proposed framework outperforms physical process models and pure neural network models while maintaining high accuracy in the case of sparse data sets. Furthermore, an attention‐mechanism input layer is integrated into the model to rank feature importance, providing global interpretation to the proposed framework. We also perform sensitivity analysis on the physical process and propose models to compare their different strategies of feature ranking. The results show that the two methods have different sensitivities to different feature patterns, but they complement each other. In summary, the proposed model is credible and stable for practical applications and has the potential to guide more efficient paddy management.

Climate change has led to increasing global air temperatures. In the field of crop cultivation, long-term high temperatures (heatwaves) during the ricegrowing season might increase the risk of high-temperature damage to rice, which might result in reductions to the yield and quality of rice. In this study, a hybrid forecast model consisting of a combined paddy field heat balance model and a meteorological forecast model is proposed for predicting 1-dayahead water temperatures as an alert system for high-temperature damage to paddy fields, with resolution in terms of hours. The results show close agreement between the measured and predicted water temperatures, and the hightemperature alert accuracy was 88.5%. Additionally, the climate resilience of paddy fields was investigated by using the rising annual temperatures due to climate change. The observations indicate that while paddy fields are sensitive to the climate, their climate resilience can be improved through artificial measures. Farmers and managers of paddy fields can thus be made aware of the water temperatures of the paddy fields in advance to enable reasonable management of water resources and avoid high-temperature damages caused by extreme weather conditions.

High ambient air and water temperatures can cause high-temperature damage to ripening rice grains after rice heading and has recently become a major issue of concern. Spill-over irrigation (also referred to as continuous irrigation with running water) is an effective countermeasure that involves simultaneous irrigation and drainage to reduce the ponded water temperature in paddy fields. However, it is necessary to understand the impact of this technique on downstream water temperatures. In this study, the discharge and water temperature variations in a dual-purpose canal (also referred to as irrigationcum-drainage canal) were measured along the main canal of the Tedori-gawa Shichika canal system in Japan. The discharge and water temperature variations in a branch drainage canal were also monitored to analyse the influence of the return flow on the water temperature in the main canal. Based on these observations, a new numerical model was developed to simulate the water temperature variations in the main canal considering meteorological conditions, heat transfer of water in the open canal, and return flow from upstream paddy fields. Finally, the model was applied to examine possible global warming scenarios and discuss the effectiveness of paddy water management in mitigating high-temperature damage in downstream paddy fields. K E Y W O R D S climate change, heat balance, high-temperature damage to rice grains, repeated use of water, spillover irrigation and paddy water management

With the development of large-scale rice cultivation management initiatives in East Asia, there is concern that a reduction in the number of human cultivators per unit area may lead to poor water management, which could result in decreased land productivity, owing to abnormal high-and low-temperature damage to crops. Accurate simulation of paddy field water temperature is important for studying its impact on crops and for providing timely information to aid in decision making for more efficient management under limited resources. We propose a neural-network framework that considers the heat transfer by the vegetation canopy and applies physical-theory constraints in its training. A novel tuning method is proposed to cope with the trade-off between water temperature accuracy and physical consistency during training to ensure that the calculated water temperature variations in a paddy field enjoy high accuracy and physical consistency. In the experiments, the proposed framework outperforms (with RMSE 0.78°C) both physical process models (with RMSE 1.06°C) and pure neural-network models (with RMSE 0.9°C) while maintaining high accuracy in the case of sparse datasets. Furthermore, an attention-mechanism input layer is integrated into the model to rank feature importance, providing global interpretation to the proposed framework. We also perform sensitivity analysis on the physical process and propose models to compare their different strategies of feature ranking. The results show that the two methods have different sensitivities to different types of feature patterns, but they complement each other. In summary, the proposed model is credible and stable for practical applications and has the potential to guide more efficient paddy management.