Forecasting actual evapotranspiration without climate data based on stacked integration of DNN and meta-heuristic models across China from 1958 to 2021.

As a non-linear phenomenon that varies along with agro-climatic conditions alongside many other factors, Evapotranspiration (ET) process represents a complexity when be assessed especially if there is a data scarcity in the weather data. However, even under such a data scarcity, the accurate estimates of ET values remain necessary for precise irrigation. So, the present study aims to: i) evaluate the performance of six hybrid machine learning (ML) models in estimating the monthly actual ET values under different agro-climatic conditions in China for seven provinces (Shandong, Jiangsu, Zhejiang, Fujian, Jiangxi, Hubei, and Henan), and ii) select the best-developed model based on statistical metrics and reduce errors between predicted and actual ET (AET) values. AET datasets were divided into 78% for model training (from 1958 to 2007) and the remaining was used for testing (from 2008 to 2021). Deep Neural Networks (DNN) was used as a standalone model at first then the stacking method was applied to integrate DNN with data-driven models such as Additive regression (AR), Random Forest (RF), Random Subspace (RSS), M5 Burned Tree (M5P) and Reduced Error Purning Tree (REPTree). Partial Auto-Correlation Function (PACF) was used for selection of the best lags inputs to the developed models. Results have revealed that DNN-based hybrid models held better performance than non-hybrid DNN models, such that the DNN-RF algorithm outperformed others during both training and testing stages, followed by DNN-RSS. This model has acquired the best values of every statistical measure [MAE (10.8, 12.9), RMSE (15.6, 17.4), RAE (31.9%, 41.4%), and RRSE (39.3%, 47.2%)] for training and testing, respectively. In contrast, the DNN model held the worst performance [MAE (14.9, 13.7), RMSE (20.1, 18.2), RAE (43.9%, 43.7%), and RRSE (50.6%, 49.3%)], for training and testing, respectively. Results from the study presented have revealed the capability of DNN-based hybrid models for long-term predictions of the AET values. Moreover, the DNN-RF model has been suggested as the most suitable model to improve future investigation for AET predictions, which could benefit the enhancement of the irrigation process and increase crop yield.

Spatio-temporal evolution and influencing factors of synergizing the reduction of pollution and carbon emissions - Utilizing multi-source remote sensing data and GTWR model.

Grasping current circumstances and influencing components of the synergistic degree regarding reducing pollution and carbon has been recognized as a crucial part of China in response to the protection of the environment and climate mitigation. With the introduction of remote sensing night-time light, CO2 emissions at multi-scale have been estimated in this study. Accordingly, an upward trend of "CO2-PM2.5" synergistic reduction was discovered, which was indicated by an increase of 78.18% regarding the index constructed of 358 cities in China from 2014 to 2020. Additionally, it has been confirmed that the reduction in pollution and carbon emissions could coordinate with economic growth indirectly. Lastly, it has identified the spatial discrepancy of influencing factors and the results have emphasized the rebound effect of technological progress and industrial upgrades, whilst the development of clean energy can offset the increase in energy consumption thus contributing to the synergy of pollution and carbon reduction. Moreover, it has been highlighted that environmental background, industrial structure, and socio-economic characteristics of different cities should be considered comprehensively in order to better achieve the goals of "Beautiful China" and "Carbon Neutrality".