Farmland landscape fragmentation is an important problem affecting the agricultural modernization process in China. However, farmland landscape fragmentation leads to land being wasted and increases management costs, particularly in the dryland’s oasis regions. Therefore, investigating the impact of farmland landscape fragmentation on agricultural irrigation is of great significance in developing oasis agriculture. This paper used the landscape quantitative index (DIVISION), the moving window method, and gradient analysis methods to study the temporal and spatial pattern changes in farmland fragmentation in the Hotan Oasis. Additionally, the impact of fragmentation on irrigation in the oasis was elaborated upon by exploring the relationship between evapotranspiration and its components in farmland fragmentation. The results showed that the farmland area of the Hotan Oasis increased from 1546.19 km² in 2000 to 2068.23 km² in 2020, and farmland landscape fragmentation increased with the expansion of the Hotan Oasis. In addition, a significant relationship between farmland fragmentation and evapotranspiration and its components was evident. A lower DIVISION value corresponded to a higher ET value, a lower ETs/ETc ratio, and a higher water use efficiency. When the total farmland area is assumed to remain unchanged, the irrigation water consumption is reduced by 4.82 × 10⁸ m³ according to the size and proportion of arable land with the lowest degree of fragmentation (L1, division value of 0.46). In addition, with the increase in the proportion of farmland, the scale of oasis decreases by 2431.56 km² for the reduction in field roads, shelterbelt, and bare land. These findings suggest that solving the problem of farmland fragmentation can effectively reduce irrigation water consumption, realize the internal expansion of the oasis through intensive land use, and relieve the pressure of the external expansion of the oasis.

With the increasing impact of human activities on the environment, evapotranspiration (ET) has changed in arid areas, which further affects the water resources availability in the region. Therefore, understanding the impact of human activities on ET and its components is helpful to the management of water resources in arid areas. This study verified the accuracy of Fisher’s model (PT-JPL model) for ET estimation in southern Xinjiang, China by using the evaporation complementarity theory dataset (AET dataset). The ET and the evapotranspiration components (T:E) of six land-use types were estimated in southern Xinjiang from 1982 to 2015, and the impact of human activities on ET was analyzed. In addition, the impact of four environmental factors (temperature (Temp), net radiation (Rn), relative humidity (RH), and NDVI) on ET were evaluated. The results showed that the calculated ET values of the PT-JPL model were close to the ET values of the AET dataset. The correlation coefficient (R²) was more than 0.8, and the NSE was close to 1. In grassland, water area, urban industrial and mining land, forest land, and cultivated land, the ET values were high, and in unused land types, the ET values were the lowest. The T:E values varied greatly in urban industrial and mining land, forest land, and cultivated land, which was due to the intensification of human activities, and the values were close to 1 in summer in recent years. Among the four environmental factors, temperature largely influenced the monthly ET. These findings suggest that human activities have significantly reduced soil evaporation and improved water use efficiency. The impact of human activities on environmental factors has caused changes in ET and its components, and appropriate oasis expansion is more conducive to regional sustainable development.

Free surface evaporation is an important process in regional water cycles and energy balance. The accurate calculation of free surface evaporation is of great significance for evaluating and managing water resources. In order to improve the accuracy of estimating reservoir evaporation in data-scarce arid regions, the applicability of the energy balance method was assessed to calculate water surface evaporation based on the evaporator and reservoir evaporation experiment. A correlation analysis was used to assess the major meteorological factors that affect water surface temperature to obtain the critical parameters of the machine learning models. The water surface temperature was simulated using five machine learning algorithms, and the accuracy of results was evaluated using the root mean square error (RMSE), correlation coefficient (r), mean absolute error (MAE), and Nash efficiency coefficient (NSE) between observed value and calculated value. The results showed that the correlation coefficient between the evaporation capacity of the evaporator, calculated using the energy balance method and the observed evaporation capacity, was 0.946, and the RMSE was 0.279. The r value between the calculated value of the reservoir evaporation capacity and the observed value was 0.889, and the RMSE was 0.241. The meteorological factors related to the change in water surface temperature were air temperature, air pressure, relative humidity, net radiation and wind speed. The correlation coefficients were 0.554, −0.548, −0.315, −0.227, and 0.141, respectively. The RMSE and MAE values of five models were: RF (0.464 and 0.336), LSSVM (0.468 and 0.340), LSTM (1.567 and 1.186), GA-BP (0.709 and 0.558), and CNN (1.113 and 0.962). In summary, the energy balance method could accurately calculate the evaporation of evaporators and reservoirs in hyper-arid areas. As an important calculation parameter, the water surface temperature is most affected by air temperature, and the RF algorithm was superior to the other algorithms in predicting water surface temperature, and it could be used to predict the missing data. The energy balance model and random forest algorithm can be used to accurately calculate and predict the evaporation from reservoirs in hyper-arid areas, so as to make the rational allocation of reservoir water resources.