Search

To determine the effects of air pollution on crop yields, weather, air pollution, and maize and winter wheat yield data from 331 cities in China from 2014 to 2016 were collected and analysed. Furthermore, support vector regression and the crop growth model were applied to extrapolate the air pollution data of Beijing and Hetian and verify the relationship between air pollution and yield. Precisely, heavy air pollution usually occurred in North China, but less than moderate air pollution levels affected crop yields statistically insignificantly. Moreover, both the winter wheat and maize yields increased in moderate air pollution periods but decreased in heavy air pollution periods in 2014, 2015 and 2016. Importantly, a threshold value was necessary for the heavy air pollution periods to trigger a yield decrease. The threshold values of maize in 2015 and 2016 were 7 days and 5 days, respectively, while that of winter wheat was 10 days in both 2015 and 2016. Once the heavy air pollution periods exceeded the threshold value, both the winter wheat and maize yields decreased linearly with the periods. PM2.5 was the main air pollutant in Beijing in 2014, while PM2.5 and PM10 were the main air pollutants in Hetian in both 2015 and 2016. Regardless of whether the main air pollutant was PM2.5 or PM10, the simulated potential winter wheat yields by the crop growth model with moderate air pollution for the whole growth period were all higher than the yields under observed and heavy air pollution conditions. [ABSTRACT FROM AUTHOR]

Copyright of Irrigation & Drainage is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Accurate estimation of pan evaporation (Ep) is vital for the development of water resources and agricultural water management, especially in arid and semi-arid regions where it is restricted to set up the facilities and measure pan evaporation accurately and consistently. Besides, using pan evaporation estimating models and pan coefficient (kp) models is a classic method to assess the reference evapotranspiration (ET0) which is indispensable to crop growth, irrigation scheduling, and economic assessment. This study estimated the potential of a novel hybrid machine learning model Coupling Bat algorithm (Bat) and Gradient boosting with categorical features support (CatBoost) for estimating daily pan evaporation in arid and semi-arid regions of northwest China. Two other commonly used algorithms including random forest (RF) and original CatBoost (CB) were also applied for comparison. The daily meteorological data for 12 years (2006–2017) from 45 weather stations in arid and semi-arid areas of China, including minimum and maximum air temperature (Tmin, Tmax), relative humidity (RH), wind speed (U), and global solar radiation (Rs), were utilized to feed the three models for exploring the ability in predicting pan evaporation. The results revealed that the new developed Bat-CB model (RMSE = 0.859–2.227 mm·d−1; MAE = 0.540–1.328 mm·d−1; NSE = 0.625–0.894; MAPE = 0.162–0.328) was superior to RF and CB. In addition, CB (RMSE = 0.897–2.754 mm·d−1; MAE = 0.531–1.77 mm·d−1; NSE = 0.147–0.869; MAPE = 0.161–0.421) slightly outperformed RF (RMSE = 1.005–3.604 mm·d−1; MAE = 0.644–2.479 mm·d−1; NSE = −1.242–0.894; MAPE = 0.176–0.686) which had poor ability to operate the erratic changes of pan evaporation. Furthermore, the improvement of Bat-CB was presented more comprehensively and obviously in the seasonal and spatial performance compared to CB and RF. Overall, Bat-CB has high accuracy, robust stability, and huge potential for Ep estimation in arid and semi-arid regions of northwest China and the applications of findings in this study have equal significance for adjacent countries. [ABSTRACT FROM AUTHOR]

Accurate precipitation (P) short-term forecasts are important for engineering studies and water allocation. This study evaluated a method for bias correction of the Numerical Weather Prediction (NWP) of Global Ensemble Forecast System V2 forecasts based on the extreme gradient boosting (XGBoost) model (M3) and 689 meteorological stations in seven different climatic regions of China. The method used a common deviation correction for multiple meteorological factors to forecast P for 1–8 d ahead. It was also compared with the equidistant cumulative distribution functions matching a single weather factor (EDCDFm, M1) and the XGBoost model (M2). The M3 method had the best forecast performance. M1, M2, and M3 methods had an average root mean square error (RMSE) ranging from 2.292–17.049 mm, 1.844–18.835 mm, and 1.819–13.608 mm, respectively. The performance of each method tended to decrease as the lead time was extended. The average false alarm ratio (increased from 55.3%, 52.8% and 50.1% to 75.8%, 82.3% and 76.0%, respectively) and miss ratio (increased from 60.9%, 53.5% and 50.3% to 76.6%, 77.7% and 71.2%, respectively) also increased with an increased lead time for all methods. The forecast performance trended downwards from northwest to southeast China. However, each method's significance in forecasting P's determination coefficient showed a contrary pattern to the forecast accuracy. There was a general underestimation across the methods. The best performance for forecasting P was achieved in winter, with root mean square error values of 2.0–3.4 mm, followed in order by autumn > spring > summer. Factor P contributed the most to forecast P after bias correction of the XGBoost model (average Gain, Cover, and Frequency values of 0.55, 0.45, and 0.29, respectively). In summary, satisfactory performance could be obtained using the XGBoost model combined with multi-factor bias correction for NWP data to forecast daily P. • The XGBoost is used to downscale and bias-correct the NWP of Global Ensemble Forecast System V2 to forecast short-term P. • Multi-factor modeling for bias correction using NWP data can be effective in improving NWP model deficiencies. • The model performs best for forecasting P in winter. [ABSTRACT FROM AUTHOR]

Drip irrigation under film mulch (DIUFM) and subsurface pipe drainage (SPD) are important measures to cope with water shortages and soil salinization in arid areas of northwest China. To investigate the coordinated operation mode of DIUFM and SPD, a new H2DSWAP model was developed based on coupling the HYDRUS-2D with a Soil–Water–Atmosphere–Plant model (SWAP). In the H2DSWAP model, real-time evapotranspiration, simple root growth, and the interaction between crops and soil water and salt are considered to improve the simulation accuracy. The model was calibrated and validated using parameter estimation and uncertainty analysis software (PEST) using field experiment datasets in 2019 and 2020 respectively. Compared with the original HYDRUS-2D model, the simulation accuracy of the H2DSWAP for soil water (root mean square error (RMSE) = 0.011 cm3·cm−3; mean absolute error (MAE) = 0.008 cm3·cm−3; determinant coefficient (R2) = 0.869) and soil salt (RMSE = 0.296 g·kg−1; MAE = 0.231 g·kg−1; R2 = 0.959) contents has been greatly improved. In addition, the simulation of the leaf area index (LAI) and yield also fitted well with field observations. The calibrated model was used to predict salt transport at depths of 0–100 cm and the change in maize yield under DIUFM. The results indicated that maize yield decreased yearly, and soil salinity increased yearly under DIUFM without SPD. Based on the obtained results, the management strategies of winter irrigation (WIR) under different drip irrigation water amounts, namely 600 mm (S1), 540 mm (S2), 480 mm (S3), and 420 mm (S4), were further investigated. Water productivity (WP) and yield were used as evaluation indices. The WIR was carried out every 4–5 years when the drip irrigation amount of the maize field was S1 and S2 was recommended. However, it was recommended to carry out WIR every 2 and 3 years under S3 and S4, respectively. Overall, the H2DSWAP model can be used as a useful tool to guide the operation mode of drip irrigation under mulch and subsurface pipe drainage in saline soils. • A new coupled H2DSWAP model was developed based on the HYDRUS-2D and SWAP. • The H2DSWAP model was calibrated and validated using experimental observations. • The soil salinity within 0–100 cm increased yearly without leaching measures. • Using the coupled H2DSWAP model to investigate optimized winter irrigation modes. [ABSTRACT FROM AUTHOR]

• The GOA-XGBoost model was the best model for estimating T dew. • The most important meteorological input was actual vapor pressure. • The hybrid modelling effects for T dew under daily and hourly scales were assessed. Dew point temperature (T dew) plays an important role in hydrology, meteorology, and other related research. This study evaluated the ability of a new machine learning model (hybrid extreme gradient boosting with grasshopper optimization algorithm (GOA-XGBoost)) to estimate T dew and compared it with two other tree-based models (XGBoost and random forest (RF)). We collected meteorological data namely actual vapor pressure (e a), maximum air temperature (T max), minimum air temperature (T min), maximum relative humidity (RH max), minimum relative humidity (RH min), atmospheric pressure (P a), 2 m high wind speed (U d), during 2016–2019 on daily and hourly time scales from the Sijiqinglin station in China to train, test, and validate each model. The results showed that the GOA-XGBoost model performed best, and the RF model had severe over-fitting problems during the validation phase at daily time scale. The models showed the best accuracy and stability when the input was e a (on average R2 = 1.000, RMSE = 0.296℃, MBE = 0.001℃, MAE = 0.167℃, and KGE = 0.991). The models had more significant errors when the inputs were T max , T min (on average R2 = 0.721, RMSE = 6.756℃, MBE = -0.101℃, MAE = 5.071℃, and KGE = 0.771). The estimation loss exhibited by the models were similar for the hourly and daily scale patterns. T and RH were the most basic meteorological factors and adding extraneous factors would affect the estimation accuracy of the model. The variability of meteorological data varied less on an hourly scale than on a daily scale. Therefore, the accuracy of the models was higher, but the data set and the volume of operations became larger. This led to a possible reduction in model stability, but the hourly scales are better suited for assessing the effects of simulations in extreme situations. Taking accuracy and stability into account, the GOA-XGBoost model was the best model and the most practical input for both time scales was e a. Therefore, in subsequent studies, the GOA-XGBoost model can be combined with the input e a to estimate T dew accurately. [ABSTRACT FROM AUTHOR]

A large amount of continuous input data is used to estimate groundwater level (GWL) by using machine learning models. However, data collection is very difficult and costly in undeveloped countries. Therefore, obtaining a general model and using less input data is the key to popularizing the application of machine learning models for estimating groundwater levels. This study evaluated the potential of the kernel-based nonlinear extension of the Arps decline model (KNEA), long short-term memory network (LSTM) and gated recurrent unit (GRU) for accurately estimating GWL in the Hetao Irrigation District in China. All models were developed using monthly records from 143 monitoring wells between 1990 and 2015. Eight input combinations (including the one-month prior GWL, air temperature, global solar radiation, precipitation and amount of irrigation) were applied to explore the possibility of improving model accuracy using less input data. In addition, the general performance of the models was evaluated by cross validation. The results showed that the KNEA model was superior to the LSTM and GRU models for all input combinations using the local application. For cross-district application, the average statistical results indicated that the LSTM (RMSE = 0.45 m and R2 = 0.78) and GRU (RMSE = 0.48 m and R2 = 0.76) models performed better than the KNEA model (RMSE = 0.70 m and R2 = 0.62), and the LSTM model achieved the highest accuracy and stability. For input data, these three models had difficulty obtaining satisfactory monthly GWLs using meteorological and irrigation data without pervious GWL data. Adding meteorological data on the basis of the historical GWL greatly improved the accuracy of the models. Compared with PREC and GSR, adding temperature input had the best improvement. However, adding large-scale average irrigation data did not significantly improve the accuracy of the models. In addition, the LSTM model and input data of the historical GWLs and temperature were recommended in arid and semiarid agricultural areas with limited data. • The ability of the LSTM, GRU, and KNE models was investigated for groundwater-level estimation. • The LSTM models outperformed the GRU and KNEA models in cross-validation. • Eight input combinations were applied to explore appropriate input. • Adding temperature improved the model accuracy on the basis of the pervious GWL. [ABSTRACT FROM AUTHOR]