Search for: All records

Abstract Vegetation plays a crucial role in atmosphere‐land water and energy exchanges, global carbon cycle and basin water conservation. Land Surface Models (LSMs) typically represent vegetation characteristics by monthly climatological indices. However, static vegetation parameterization does not fully capture time‐varying vegetation characteristics, such as responses to climatic fluctuations, long‐term trends, and interannual variability. It remains unclear how the interaction between vegetation and climate variability propagates into hydrologic fluxes and water resources. Multi‐source satellite data sets may introduce uncertainties and require extensive time for analysis. This study developes a deep learning surrogate for a widely used LSM (i.e., Noah) as a rapid diagnosic tool. The calibrated surrogate quantifies the impacts of time‐varying vegetation characteristics from multiple remotely sensed GVF products on the magnitude, seasonality, and biotic and abiotic components of hydrologic fluxes. Using the Upper Colorado River Basin (UCRB) as a test case, we found that time‐varying vegetation provides more buffering effect against climate fluctuation than the static vegetation configuration, leading to reduced variability in the abiotic evaporation components (e.g., soil evaporation). In addition, time‐varying vegetation from multi‐source remote sensing products consistently predicts smaller biotic evaporation components (e.g., transpiration), leading to increased water yield in the UCRB (about 14%) compared to the static vegetation scheme. We also highlight the interaction between dynamic vegetation parameterization and static parameterization (e.g., soil) during calibration. Parameter recalibration and a re‐evaluation of certain model assumptions may be required for assessing climate change impacts on vegetation and basin‐wide water resources. 

Abstract Reservoirs are designed and operated to mitigate hydroclimatic variability and extremes to fulfill various beneficial purposes. Existing reservoir infrastructure capacity and operation policies derived from historical records are challenged by hydrologic regime change and storage reduction from sedimentation. Furthermore, climate change could amplify the water footprint of reservoir operation (i.e. non-beneficial evaporative loss), further influencing the complex interactions among hydrologic variability, reservoir characteristics, and operation decisions. Disentangling and quantifying these impacts is essential to assess the effectiveness of reservoir operation under future climate and identify the opportunities for adaptive reservoir management (e.g. storage reallocation). Using reservoirs in Texas as a testing case, this study develops data-driven models to represent the current reservoir operation policies and assesses the challenges and opportunities in flood control and water supply under dynamically downscaled climate projections from the Coupled Model Intercomparison Project Phase 6. We find that current policies are robust in reducing future flood risks by eliminating small floods, reducing peak magnitude, and extending the duration for large floods. Current operation strategies can effectively reduce the risk of storage shortage for many reservoirs investigated, but reservoir evaporation and sedimentation pose urgent needs for revisions in the current guidelines to enhance system resilience. We also identify the opportunities for reservoir storage reallocation through seasonal-varying conservation pool levels to improve water supply reliability with negligible flood risk increase. This study provides a framework for stakeholders to evaluate the effectiveness of the current reservoir operation policy under future climate through the interactions among hydroclimatology, reservoir infrastructure, and operation policy. 

The exacerbated thermal environment in cities, the urban heat island (UHI) effect as a prominent example, has been the source of many adverse urban environmental issues, including the increase of health risks, degradation of air quality and ecosystem services, and reduced resiliency of engineering infrastructure. Last decades have witnessed tremendous efforts and resources being invested to find sustainable solutions for urban heat mitigation, whereas the relative contributions of different UHI attributes and their patterns of spatio-temporal variability remain obscure. In this study, we employed the random forest (RF) method to quantify the relative importance of four categories of urban surface characteristics that regulate the surface UHI, namely the urban greenery fraction, land surface albedo, urban morphology, and level of human activities. We selected seventeen major cities from six megaregions in China as our study areas, with the RF training and test sets obtained from multi-sourced remote sensing and observational data products. It is found that the urban greenery coverage manifests as the most important environmental determinants of UHI, followed by surface albedo. The results are informative for urban planners, policymakers, and engineering practitioners to design and implement sustainable strategies for urban heat mitigation. 

Abstract In many regions globally, snowmelt‐recharged mountainous karst aquifers serve as crucial sources for municipal and agricultural water supplies. In these watersheds, complex interplay of meteorological, topographical, and hydrogeological factors leads to intricate recharge‐discharge pathways. This study introduces a spatially distributed deep learning precipitation‐runoff model that combines Convolutional Long Short‐Term Memory (ConvLSTM) with a spatial attention mechanism. The effectiveness of the deep learning model was evaluated using data from the Logan River watershed and subwatersheds, a characteristically karst‐dominated hydrological system in northern Utah. Compared to the ConvLSTM baseline, the inclusion of a spatial attention mechanism improved performance for simulating discharge at the watershed outlet. Analysis of attention weights in the trained model unveiled distinct areas contributing the most to discharge under snowmelt and recession conditions. Furthermore, fine‐tuning the model at subwatershed scales provided insights into cross‐subwatershed subsurface connectivity. These findings align with results obtained from detailed hydrogeochemical tracer studies. Results highlight the potential of the proposed deep learning approach to unravel the complexities of karst aquifer systems, offering valuable insights for water resource management under future climate conditions. Furthermore, results suggest that the proposed explainable, spatially distributed, deep learning approach to hydrologic modeling holds promise for non‐karstic watersheds. 

Abstract Snow dominated mountainous karst watersheds are the primary source of water supply in many areas in the western U.S. and worldwide. These watersheds are typically characterized by complex terrain, spatiotemporally varying snow accumulation and melt processes, and duality of flow and storage dynamics because of the juxtaposition of matrix (micropores and small fissures) and karst conduits. As a result, predicting streamflow from meteorological inputs has been challenging due to the inability of physically based or conceptual hydrologic models to represent these unique characteristics. We present a hybrid modeling approach that integrates a physically based, spatially distributed, snow model with a deep learning karst model. More specifically, the high‐resolution snow model captures spatiotemporal variability in snowmelt, and the deep learning model simulates the corresponding response of streamflow as influenced by complex surface and subsurface properties. The deep learning model is based on the Convolutional Long Short‐Term Memory (ConvLSTM) architecture capable of handling spatiotemporal recharge patterns and watershed storage dynamics. The hybrid modeling approach is tested on a watershed in northern Utah with seasonal snow cover and variably karstified carbonate bedrock. The hybrid models were able to simulate streamflow at the watershed outlet with high accuracy. The spatial and temporal recharge and discharge patterns learned by the ConvLSTM model were then examined and compared with known hydrogeologic information. Results suggest that ConvLSTM simulates streamflow with higher accuracy than reference models for the study area and provides insight into spatially influenced hydrologic responses that are unavailable within lumped modeling approaches.