Search

Agroecosystems are facing the adverse effects of climate change. This study explored how the ECOsystem Spaceborne Thermal Radiometer Experiment on Space Station (ECOSTRESS) can give new insight into irrigation allocation and plant health. Leveraging the global coverage and 70-m spatial resolution of the Evaporative Stress Index (ESI) from ECOSTRESS, we processed over 200 overpasses and examined patterns over 3 growing seasons across the Maipo River Basin of Central Chile, which faces exacerbated water stress. We found that ECOSTRESS ESI varies substantially based on the overpass time, with ESI values being systematically higher in the morning and lower in the afternoon. We also compared variations in ESI against spatial patterns in the environment. To that end, we analyzed the vegetation greenness sensed from Landsat 8 and compiled the referential irrigation allocation from Chilean water regulators. Consistently, we found stronger correlations between these variables and ESI in the morning time (than in the afternoon). Based on our findings, we discussed new insights and potential applications of ECOSTRESS ESI in support of improved agricultural monitoring and sustainable water management.

Irrigated areas are major vectors of agricultural development and components of ecosystems. The groundwater level maintains the irrigated areas’ ecology safety and sustainable development. Under the influence of irrational irrigation practices—such as flood irrigation or extreme water saving without consideration of ecological impact—different areas within an irrigation district may experience anomalies in groundwater levels (either too deep or too shallow). It is of great significance to carry out research on water resource allocation and future water-saving strategies, taking into consideration groundwater depths. In this study, a method for the optimal allocation of irrigation water resources that considered groundwater level was used to regulate irrational irrigation practices and to reveal the future direction of water saving. Helan County in Ningxia province, an ecologically fragile and arid irrigated area, was selected as a case study. Multiple scenarios of different water use and different degrees of water-saving were analyzed. The results showed that non-engineering water-saving measures (such as adjusting the planting structure and controlling the amount of irrigation for rice) had better benefits compared to engineering measures (such as efficient water-saving irrigation and channel lining). When implementing only one water-saving measure, the strategy of replacing 75% of the rice area with corn yielded the best results. This approach can reduce the irrigation water shortage rate to 11% and increase by 4.58% the acreage where the groundwater level is reasonable. When multiple water-saving measures are implemented together, the most effective strategy for future water-saving efforts involves the joint implementation of several measures: replacing 75% of the rice area with corn, limiting irrigation for rice to no more than 11.85 thousand m3/ha, adopting high-efficiency water-saving irrigation in 90% of the pump-diverted water irrigation region and 40% of the channel-diverted water irrigation region, and maintaining the channel’s water utilization coefficient at 0.62. This strategy can keep the irrigation water shortage below 3.66% and increase the acreage where the groundwater level is reasonable, by 4.58% per year. The conclusions and research approaches can provide references for the formulation of water-saving measures for irrigated areas’ sustainable development.

The type of single-slope solar greenhouse is mainly used for vegetable production in China. The coupling of heat storage and release courses and the dynamic change in the outdoor weather parameters momentarily affect the indoor environment. Due to the high cost of small weather stations, the environmental parameters monitored by the nearest meteorological stations are usually used as outdoor environmental parameters in China. In order to accurately predict the solar greenhouse and crop water demand, this paper proposes three deep learning models, including neural network regression (DNNR), long short-term memory (LSTM), and convolutional neural network-long- short-term memory (CNN-LSTM), and the hyperparameters of three models were determined by orthogonal experimental design (OD). The temperature and relative humidity monitored by the indoor sensors and outdoor weather station were taken as the inputs of models, the temperature and relative humidity 3, 6, 12 and 24 h in advance were taken as the output, 16 combinations of input and output data of two typical solar greenhouses were trained separately by three deep learning models, those models were trained 144, 144 and 288 times, respectively. The best model of three type models at four prediction time points were selected, respectively. For the forecast time point of 12 h in advance, the errors of the best LSTM and CNN-LSTM models in two greenhouses were all smaller than the DNNR models. For the three other time points, the results show that the DNNR models have excellent prediction accuracy among the three models. The maximum and minimum temperature, relative humidity, and ETo were also accurately predicted using the corresponding optimized models. In sum, this study provided an optimized deep learning prediction model for environmental parameters of greenhouse and provides technical support for irrigation decision-making and water allocation.