Search

Soil temperature directly affects the germination of seeds and the growth of crops. In order to accurately predict soil temperature, this study used RF and MLP to simulate shallow soil temperature, and then the shallow soil temperature with the best simulation effect will be used to predict the deep soil temperature. The models were forced by combinations of environmental factors, including daily air temperature (Tair), water vapor pressure (Pw), net radiation (Rn), and soil moisture (VWC), which were observed in the Hejiashan watershed on the Loess Plateau in China. The results showed that the accuracy of the model for predicting deep soil temperature proposed in this paper is higher than that of directly using environmental factors to predict deep soil temperature. In testing data, the range of MAE was 1.158–1.610 °C, the range of RMSE was 1.449–2.088 °C, the range of R2 was 0.665–0.928, and the range of KGE was 0.708–0.885 at different depths. The study not only provides a critical reference for predicting soil temperature but also helps people to better carry out agricultural production activities.

Irrigation water is the main type of water consumption in the Yanqi Basin irrigation district of Xinjiang, which is an oasis-type irrigation district in the arid region of Northwest China. With the continuous expansion of cultivated areas, there is an increasing demand for irrigation water, resulting in an irrigation efficiency paradox and the phenomenon of “the more water-saving, the more water-scarce”. In this study, the water balance method and the improved IWMI (International Water Management Institute) water balance method were used with remote sensing and statistical data from 1980 to 2020 to analyze the changes in the irrigation water supply, consumption, and loss for improvement in irrigation water use efficiency (IWUE) in the Yanqi Basin. The results showed that there was an upward trend in the cultivated land area in the irrigation district of Yanqi Basin, as monitored with remote sensing from 1980 to 2020, and the values from the remote sensing data were higher than those from the yearbooks. According to the remote sensing data, the arable land area in the irrigation district increased from 1672 km2 in 1980 to 2494 km2 in 2020, thus showing a trend of expansion. The traditional water use efficiency in the irrigation district showed an increasing trend. The lowest value for the field water-use coefficient was 0.70 in 1998, and it exceeded to 0.81 from 2009 to 2020. The canal water-use coefficient was as low as 0.50 in 1998 and increased from 0.54 in 2009 to 0.82 in 2020. The irrigation water-use coefficient increased from 0.35 in 1998 to 0.68 in 2020, with a general upward trend. In this study, the water consumption ratio indicator DFg (depleted fraction), determined using the improved water balance method, increased from 0.8390 in 1980 to 0.8562 in 2020, although it showed an overall decreasing trend, and the average was 0.8436. Cultivated land’s actual irrigation water consumption per unit area reached the highest value of 8.41 × 106 m3/hm2/a in 2011 and the minimum value of 4.01 × 106 m3/hm2/a in 2020, and from 1980 to 2020 it showed a decreasing trend, while the total water diversion showed an increasing trend due to the continuous expansion of arable land. From 1980 to 2020, water diversion into the irrigation district changed from 1.214 km3 to 1.000 km3, and it reached a maximum of 1.593 km3 in 2000; water diversion into the irrigation district showed an overall upward trend. The positive impact of the post-2000 water conservation phase with the adaptation of water-saving irrigation technology was clear, as the findings showed an increase in IWUE in the Yanqi Basin irrigation district. These results provide a theoretical basis for breaking the paradox of irrigation efficiency, which can be used in the water resource management of irrigation districts.