Artificial intelligence (AI) is increasingly essential for optimizing energy systems, addressing the growing complexity of energy management, and supporting the integration of diverse renewable sources. This study systematically reviews AI-enabled modeling approaches, highlighting their applications, limitations, and potential in advancing sustainable energy systems while offering insights and a framework for addressing real-world energy challenges. Data-driven models excel in energy demand prediction and resource optimization but face criticism for their “black-box” nature, while mechanism-driven models provide deeper system insights but require significant computation and domain expertise. To bridge the gap between these approaches, hybrid models combine the strengths of both, improving prediction accuracy, adaptability, and overall system optimization. This study discusses the policy background, modeling approaches, and key challenges in AI-enabled energy system modeling. Furthermore, this study highlights how AI-enabled techniques are paving the way for future energy system modeling, including integration and optimization for renewable energy systems, real-time optimization and predictive maintenance through digital twins, advanced demand-side management for optimal energy use, and hybrid simulation of energy markets and business behavior.

An in-depth study of the temporal and spatial distribution of pollution loads can assist in the development of water pollution remediation. The research scope of this paper was the highly developed Wuhu City located south of the Yangtze River. Chemical oxygen demand (COD), NH₃-H, and total phosphorus (TP) were chosen as the pollutant research objects of this study. Then, by combining the natural and social conditions within the scope of the study, a balanced system of pollution load generation and migration was described. A pollution load model of Wuhu City based on Load Calculator, MIKE 11, and ArcGIS was established. The results indicate that, in terms of the time distribution, the changes in the influx of the different pollutants were consistent. In terms of the spatial distribution, the major contributions to the annual pollution load were domestic pollution, urban surface runoff pollution, and poultry breeding pollution. The major contributors to the annual pollution load into the river were domestic pollution, urban surface runoff pollution, and sewage plant tail water pollution. This analysis provides references for the comprehensive management of local water environments.

This study focuses on the nitrogen removal capability of the mangrove wetland system towards resolving the excessive inorganic nitrogen content in the marine water of Shenzhen’s Deep Bay. The nitrogen distribution characteristics, biological nitrogen removal processes, nitrogen removal functional genes, and bacterial community characteristics were investigated in five wetland sites in the intertidal zone of the Deep Bay, viz. the Kandelia candel, Bruguiera gymnorrhiza, Sonneratia apetala, Aegiceras corniculatum, and mud flat sites. The results showed that ammonia and nitrate in the marine water were significantly removed in the five wetlands sites, with respective removal efficiencies of 70.9–75.5% and 89.5–94.0%. The concentration of ammonia and nitrate in pore water remained significantly unchanged with depth. Denitrification and anammox were each system’s main biological nitrogen removal processes, and their rates were 1.70–3.22 and 0.07–0.36 μmol/(kg·h), respectively. The denitrification rates in the mangroves were higher than in the mud flat site, unlike the anammox rates. The denitrifying functional genes (nirS, nosZ) and anammox functional gene (hzsB) showed an excellent linear relationship with the relevant process rates. Bacillus and Pseudomonas were the main heterotrophic denitrifying bacteria genera identified. The autotrophic denitrifying bacteria genus Sulfurovum was also identified in the systems, while Candidatus Scalindua was the only anammox genus identified in this study. The results of this study improve our understanding of the nitrogen removal characteristics of coastal wetlands and the role of mangrove plants in the biological nitrogen removal processes.

Accurate projection of floods is of great significance to safeguard economic and social development as well as people’s life and property. The development of hydrological models can improve the level of flood projection, however, the numerous uncertainties in the models limit the projection accuracy. By adding observations to correct the operation of prediction models, the accuracy can be improved to some extent. In this paper, taking the Xun River, of the Hanjiang River Basin in China, as the research object, combined with the soil moisture satellite data obtained by the soil moisture active and passive satellite (SMAP), the ensemble Kalman filter (EnKF) algorithm was used to assimilate the upper soil water content (WU) of the Xinanjiang model. In addition, based on the simultaneous assimilation of state variables and parameters, two improved assimilation schemes were proposed here, namely, the augmented ensemble Kalman filter (AEnKF) scheme and the dual ensemble Kalman filter (DEnKF) scheme. The results showed that compared with the WU assimilation scheme, the simultaneous assimilation of parameters and WU improved the prediction ability of the Xinanjiang model to a greater extent. The two improved schemes had similar effects on flood prediction accuracy, and improved the overall Nash–Sutcliffe efficiency coefficient (NSE) from 0.725 for non-assimilated, and 0.758 for assimilated WU, to 0.781. Among them, AEnKF and DEnKF schemes, respectively, improved the NSE by 10.1% and 11% at maximum. This study demonstrated that the application of data assimilation for the Xun River effectively improved the flood forecast accuracy of the Xinanjiang model, which will provide a reference basis and technical support for future flood prevention and mitigation and flood projection in this basin.

Non-point source pollution inflow is one of the main causes of water quality decline in urban river networks. In this paper, aiming at the problem of non-point source pollutant transport in river network, the lateral outflow term in the Saint-Venant equation is improved from the previous constant to the time-varying flow process, and a mathematical model considering the time-varying source and sink term is established. Based on the initial rainfall intensity, surface confluence and non-point source pollutant concentration, a method for calculating the time-varying lateral pollutant input of nodes and tributaries with linear increase and exponential decay in the initial rainfall period is proposed. Based on the principle of proximity, the watershed is divided into districts. According to the principle of elevation, the non-point source pollutants are allocated to the calculation nodes of adjacent rivers in a certain proportion and incorporated into the model calculation so as to improve the mathematical model of river network water quality and apply it to the simulation of river network water quality in Maozhou River Basin. Verified by the measured data, the NSE values of the improved model are 0.805 and 0.851, respectively, indicating that the model has reliable hydrodynamic and water quality simulation accuracy, indicating that the model can be applied to the calculation of non-point source pollutants in the basin. Based on the improved model, the variation of COD concentration in the Maozhou River of Shenzhen before and after optimized water replenishment was calculated, and the time variation and spatial distribution law of the sudden drop of water quality in the river network caused by the inflow of non-point source pollution in the initial rainfall runoff and the rapid recovery after optimized water replenishment were revealed.

The ecosystems of the Yarlung Tsangpo River Basin (YTRB) are fragile and sensitive to climate change, so an in-depth analysis of the relationship between the vegetation dynamics in the YTRB and climate change is crucial to understand regional and global climate change. This study quantified the spatial and temporal characteristics of the vegetation cover and meteorological elements in the YTRB over the past four decades. The evapotranspiration data were corrected by combining the characteristics of the vegetation in the region in order to systematically explore the relationship between the vegetation change and climate change response in the YTRB. The results indicated that the fractional vegetation cover (FVC), air temperature (ATEM) and precipitation (PRE) showed a significant increase during 1981–2020, with a variable speed of 0.05/10a, 0.38 °C/10a, and 13.3 mm/10a. The actual evapotranspiration (AET) decreased significantly (32.8 mm/10a). There were positive effects of the increased ATEM and decreased AET on the increase in FVC, with ATEM as the leading factor of influence. After excluding the influence of other factors, the degree of influence of PRE on FVC increased to 2.5 times of the original, and the AET increased by 28.57%. The three climate factors synergistically contribute to the positive development of FVC in 47.43% of the upper and middle sections of the YTRB.