Deep learning (DL) models have demonstrated exceptional performance in hydrological modeling; however, they are limited by their inability to output untrained hydrological variables and lack of interpretability compared to process-based hydrological models. We propose a hybrid approach that combines the conceptual EXP-Hydro model with embedded neural networks (ENNs), replacing its internal modules while maintaining adherence to hydrological knowledge. The resulting hybrid model can predict untrained hydrological variables without requiring post-processing or pre-training procedures. We tested 15 hybrid models that replace different internal modules across 569 basins in the contiguous United States using the CAMELS dataset. Additional experiments were conducted to generalize hydrological relationships within ENNs and further use them to improve the EXP-Hydro model's performance. Results show that all hybrid scenarios outperform the ordinary EXP-Hydro model, with an optimal median Nash-Sutcliffe efficiency (NSE) of 0.701 in the evaluation period – comparable to state-of-the-art LSTM and conceptual hydrological model featuring an error-correcting post-processor. Reasonable patterns of runoff and snow-related processes are captured by ENNs in respective hybrid models. We further used the runoff (snow-related) pattern to improve the ordinary EXP-Hydro model with median NSE increasing from 0.496 to 0.567 (raising median NSE from 0.601 to 0.677 in snow-influenced region). Our study highlights the potential for using ENNs in enhancing process-based hydrological models' performance while maintaining interpretability within a novel hybrid framework. 

Enhancing process-based hydrological models with embedded neural networks: A hybrid approach

The quantitative attribution of climate change to runoff increase over the Qinghai-Tibetan Plateau.

High Mountain Asia (HMA) is the headwater area for major Asian rivers, providing a vast amount of freshwater to billions of people in Asia. These rivers also make their surrounding areas highly vulnerable to destructive water-related disasters. However, the complex spatiotemporal variability of runoff over HMA and its underlying mechanisms are poorly understood. This study investigates into the spatial heterogeneity of HMA’s runoff variability at three timescales (interannual, interdecadal, and multidecadal) and the roles played by climate conditions and catchment properties. We find significant interannual and multidecadal variability of runoff in west and central HMA, and significant interdecadal variability in central and east HMA. At interannual and multidecadal timescales, the runoff variability tends to be more significant in dryer basins. The variability of runoff at the three timescales is largely controlled by climate variations, especially precipitation. The catchment properties, including groundwater storage and glacier-snow meltwater, also play important roles in regulating the effect of precipitation. In particular, the high contributions of glacier-snow meltwater in east HMA can weaken the response of runoff variability to precipitation at interannual and multidecadal timescales. The space-time patterns of runoff variability over HMA are driven by atmospheric drivers including El Niño-Southern Oscillation, Interdecadal Pacific Oscillation and Atlantic Multidecadal Oscillation across timescales. The results of this study provide a better understanding of HMA’s runoff variability and its physical mechanisms, which have critical implications for sustainable freshwater management and effective risk mitigation in this densely populated and ecologically vulnerable region. This article is protected by copyright. All rights reserved. 

Heterogeneity in Spatiotemporal Variability of High Mountain Asia's Runoff and Its Underlying Mechanisms


The Tibetan Plateau (TP) has become wetter and warmer during the past four decades, which leads to an adjustment in the surface energy budget, characterized by enhanced surface latent heat and weakened surface sensible heat. However, the impacts of these surface energy changes on climate are unclear. In this study, we investigate the atmospheric response to the altered surface energy budget in the monsoon season over the TP using regional climate simulations. The inhibited surface sensible heating weakens the thermal effect of the TP, which further suppresses low-level convergence and upper-level divergence, thereby weakening the water vapor flux convergence over the plateau. The weakening of low-level air humidity by this dynamical response exceeds the supply from the enhanced surface evaporation, causing decreased precipitation (decreasing more in the wet eastern plateau and less in the dry west). Further analyses show that the precipitation frequency increases mainly for light precipitation while decreasing for heavy precipitation. It is thus demonstrated that on the TP, land surface energy–atmosphere interactions can mitigate the rate of precipitation increase, suppress the increase in frequency of heavy precipitation, and weaken the east–west contrast in precipitation amount, through a dynamical mechanism. Overall, land–atmosphere interactions on the TP exert negative feedback to partially offset the accelerated plateau water cycle under a changing climate.

Land–Atmosphere Interactions Partially Offset the Accelerated Tibetan Plateau Water Cycle through Dynamical Processes

Disaster effects of climate change in High-Mountain Asia: State of art and scientific challenges

Previous projections show consistent increases in river flows of Asian Water Towers under future climate change. Here we find non-monotonic changes in river flows for seven major rivers originating from the Tibetan Plateau at the warming levels of 1.5 °C, 2.0 °C, and 3.0 °C based on an observation-constrained hydrological model. The annual mean streamflow for seven rivers at 1.5 °C warming level decreases by 0.1-3.2% relative to the present-day climate condition, and increases by 1.5-12% at 3.0 °C warming level. The shifting river flows for the Yellow, Yangtze, Brahmaputra, and Ganges are mostly influenced by projected increases in rainfall, but those for the Mekong, Salween, and Indus are dictated by the relative changes in rainfall, snowmelt and glacier melt. Reduced river flows in a moderately warmed climate threaten water security in riparian countries, while elevated flood risks are expected with further temperature increases over the Tibetan Plateau. 

/pdf/non-monotonic-changes-in-asian-water-towers-streamflow-at-i9hep2fn.pdf

Non-monotonic changes in Asian Water Towers’ streamflow at increasing warming levels

As a crucial variable in hydrological and climate modeling, a lot of efforts have been made to estimate the evaporation (E, including soil evaporation, canopy interception, and plant transpiration) on the Tibetan Plateau (TP). Most studies showed that the evaporation on the TP stops increasing or even decreases in the recent two decades. However, the spatio‐temporal variability of this phenomenon and its underlying mechanism remains uncertain. Here, we utilized a state‐of‐the‐art version of the sigmoid generalized complementary equation to estimate the monthly evaporation over the TP for the period of 1979–2018. The results show that the annual E increases significantly during 1979–1998 with a rate of 1.94 mm yr−1 (based on the total E over the TP), however, it decreases during 1999–2018 with a rate of −1.06 mm yr−1. The most significant decreasing trend of E occurs in the spring. The areas with the most significant decrement of E include the central and western Qiangtang Plateau, the middle reaches of Yarlung Zangbo River, and the Yangtze River basin. By introducing a new aridity index Rwe, we identified that the decrement of E mainly occurs in the water‐limited regions, which contribute to 60% of the total decreasing trend of the whole region; at the same time, the energy‐limited regions also contribute to 40% of the decreasing trend. This study is important for the hydrological researches and decision making because the trend of E can influence the water resources and agriculture.

The Evaporation on the Tibetan Plateau Stops Increasing in the Recent Two Decades

The nexus between atmospheric moisture transport and basin‐scale flood response is still lacking over the Third Pole (TP) region, despite projected increases in extreme rainfall under a changing climate. Based on long‐term daily streamflow observations, we show that peaks‐over‐threshold floods over the Yarlung Zangbo River (YZR) basin show two temporal clusters, that is, July and late August, with the flood magnitudes of the second cluster larger than the first by 20%. These floods are resultant from a mixture of flood‐producing storms with contrasting storm motion and moisture transport pathways. A suite of coupled atmospheric‐hydrological modeling experiments further quantify the impacts of different moisture transport pathways on the space‐time rainfall structure and flood response. A 50% reduction of upper level moisture transport (i.e., through the upslope of the Himalayas) leads to decreased flood peak magnitudes by 30% at the basin outlet for the August 1998 floods over the YZR basin. Upper‐level moisture transport is associated with the notable low pressure over the central‐east India and westward extension of West Pacific Subtropical High that enhances convergence of water vapor fluxes from Bay of Bengal toward TP. The magnitude of impact can potentially alter the seasonal clustering of high‐flow events over TP. Our analyses contribute to improved characterization of flood risk over TP, and advances in flood frequency hydrology.

Flood Seasonality Over the Third Pole Region Modulated by Upper Level Moisture Transport

The Tibetan Plateau is the headwaters of several major river basins, but uncertainties exist in the estimated contributions of glacial melt and groundwater to runoff. We present a new tracer-aided glacio-hydrological model constrained by multiple datasets for five major river basins of the Tibetan Plateau. We show that the contribution of glacier melt to the annual runoff is less than 5% in all the five basins at the outlets—much less than previous estimates. Our secondary finding is that the partitioning between surface runoff and groundwater flow varied greatly across the watersheds, with groundwater runoff contributing 35–75% of the annual runoff. The contribution of glacier melt has a strong spatial variability and scale dependency, but the population heavily dependent on it is limited, so a potential significant decrease in water resources due to glacier shrinkage is not a problem that should raise public worries in the Tibetan Plateau.

Glacier meltwater has limited contributions to the total runoff in the major rivers draining the Tibetan Plateau

Popular Tasks used by Researchers

How can I help with your research?

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

We encountered an error while loading the panel. Please try refreshing the page.

Something went wrong

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

Anyone with the link can view this chat. You can switch it back to private anytime.

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Kunbiao Li

Author Tools

Chat about Author

Papers

Non-monotonic changes in Asian Water Towers’ streamflow at increasing warming levels

The Evaporation on the Tibetan Plateau Stops Increasing in the Recent Two Decades

Flood Seasonality Over the Third Pole Region Modulated by Upper Level Moisture Transport

Glacier meltwater has limited contributions to the total runoff in the major rivers draining the Tibetan Plateau