VBVidushi Bigler

Vidushi Bigler

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Vidushi Bigler has a total of 7 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    How Graph Design Shapes Spatio-Temporal River Water Temperature Modeling

    by Benjamin Fankhauser, Vidushi Bigler, Kaspar Riesen

    River water temperature modeling is important for environmental monitoring and water management, especially under climate change. Recent approaches use graph-based representations to capture spatial dependencies between monitoring stations, typically based on hydrological flow. However, it remains unclear which graph structures are most suitable for representing river systems. This paper systematically evaluates the impact of various graph construction. We compare Natural Flow Graphs, Relative Neighbor Graphs, Gabriel Graphs, Delaunay Triangulation Graphs, and k-nearest Neighbor Graphs across three real-world datasets using a spatio-temporal graph neural network for air-to-water modeling. Results show that hydrological flow graphs provide a strong baseline but are not consistently optimal. Proximity-based structures often achieve lower prediction errors, with Gabriel, Delaunay, and moderately dense k-nearest Neighbor Graphs performing best. An ablation study replacing graph neural networks with multi-head self-attention achieves competitive performance but does not outperform graph-based approaches. Overall, graph construction substantially influences predictive performance.

  • Open Access

    Benchmarking Graphs and Embeddings for River Temperature Prediction

    by Benjamin Fankhauser, Vidushi Bigler, Kaspar Riesen

    In climate research, modeling river water temperature is a key pattern recognition task for detecting trends and predicting change. As a geospatial time series problem, its predictive performance is highly sensitive to sensor choice and temporal coverage, limiting comparability across studies. As the first major contribution, we curate three river water temperature datasets with a well-defined experimental setup specifying sensor choice and temporal partitions to enable fair and robust comparisons across diverse scenarios. Building on this foundation, our second major contribution examines the role of learnable embeddings and structural information -- two recently introduced concepts in river water temperature modeling. To this end, we evaluate four models representing all combinations of these components: LSTM, Graphlet, LSTM-E, and ST-GNN (a spatio-temporal graph neural network). Our experiments corroborate the predictive performance reported in prior studies, while revealing substantial variability across water stations. Crucially, we provide statistical evidence that structural information consistently enhances baseline models across all datasets. Moreover, the marked reduction in learnable parameters -- a defining feature of embedding-based methods -- demonstrates their efficiency and underscores their potential for future river water temperature modeling architectures.

  • Benchmarking Transformers on Spatio-Temporal River Water Temperature Modeling

    by Linlin Jia, Benjamin Fankhauser, Vidushi Bigler, Kaspar Riesen


  • Open Access

    Multi-fidelity model assessment of climate change impacts on river water temperatures and thermal extremes and potential effects on cold-water fish in Switzerland

    by Love Råman Vinnå, Vidushi Bigler, Oliver S. Schilling, Jannis Epting

    River water temperature is a key factor for water quality, aquatic life, and human use. Under climate change, inland water temperatures have increased and are expected to do so further, increasing the pressure on aquatic life and reducing the potential for human use. Here, future river water temperatures are projected for Switzerland based on a multi-fidelity modeling approach. We use 2 different semi-empirical surface water temperature models, 22 coupled and downscaled general circulation to regional climate models, future projections of river discharge from 4 hydrological models, and 3 climate change scenarios (RCP2.6, 4.5, and 8.5). By grouping catchments under representative thermal regimes and by employing hierarchical cluster-based thermal-pattern recognitions, an optimal model and model configuration were selected, thereby improving model performance. Results show that, until the end of the 21st century, average river water temperatures in Switzerland will likely increase by 3.2 ± 0.7 °C (or 0.36 ± 0.1 °C per decade) under RCP8.5, while, under RCP2.6, the temperature increase may remain at 0.9 ± 0.3 °C (0.12 ± 0.1 °C per decade). Under RCP8.5, temperatures of rivers classified as being in the Alpine thermal regime will increase the most, that is, by 3.5 ± 0.5 °C, followed by rivers of the Downstream Lake regime, which will increase by 3.4 ± 0.5 °C. Under RCP2.6, temperatures in the Alpine and Downstream Lake regimes change most, with +1.15 and +0.99 ± 0.5 °C. A general pattern of decreasing river discharge in summer (−10 % to −40 %) and increasing river discharge in winter (+10 % to +30 %), combined with a further increase in average near-surface air temperatures (0.5 °C per decade), bears the potential to result in not only overall warmer rivers but also prolonged periods of extreme summer river water temperatures. This dramatically increases the thermal-stress potential for temperature-sensitive aquatic species such as the brown trout in rivers where such periods occur already but also in rivers where this was previously not a problem. By providing information on future water temperatures, the results of this study can guide the management of climate mitigation efforts.


  • Exploring a Graph Regression Problem in River Networks

    by Benjamin Fankhauser, Vidushi Bigler, Kaspar Riesen

  • Open Access

    Reply on RC3

    by Love Raman Vinna, Vidushi Bigler, Oliver S. Schilling, Jannis Epting

    River water temperature is a key factor for water quality, aquatic life, and human use. Under climate change, inland water temperatures have increased and are expected to do so further, increasing the pressure on aquatic life and reducing the potential for human use. Here, future river water temperatures are projected for Switzerland based on a multi-fidelity modelling approach. We use 2 different, semi-empirical surface water temperature models, 22 coupled and downscaled general circulation- to regional climate models, future projections of river discharge from 4 hydrological models and 3 climate change scenarios (RCP2.6, 4.5, and 8.5). By grouping stream sections, catchments and spring-fed water courses under representative thermal regimes, and by employing hierarchical cluster-based thermal pattern recognition, an optimal model and model configuration was selected, model performance optimized and climate change impact assessment on river water temperatures improved. Results show that, until the end of the 21st century, average river water temperatures in Switzerland will likely increase by 3.1±0.7 °C (or 0.36±0.1 °C per decade) under RCP8.5, while under RCP2.6 the temperature increase may remain at 0.9±0.3 °C (0.12±0.1 °C per decade). Under RCP8.5, temperatures of rivers classified as being in the Alpine thermal regime will increase the most, that is, by 3.5±0.5 °C, followed by rivers of the Downstream Lake regime, 3.4±0.5 °C. A general decrease of river discharge in summer (-10 to -40 %) and increase in winter (+10 to +30 %), combined with a further increase in average near-surface air temperatures (0.5 °C per decade), bears the potential to not only result in overall warmer rivers, but also in prolonged periods of extreme summer river water temperatures. This dramatically increases the thermal stress potential for temperature sensitive aquatic species such as the brown trout in rivers where such periods occur already, but also rivers in where this previously was not a problem. By providing information of future water temperatures, the results of this study can guide managements climate mitigation efforts.

  • Open Access

    Reply on RC1

    by Love Raman Vinna, Vidushi Bigler, Oliver S. Schilling, Jannis Epting

    River water temperature is a key factor for water quality, aquatic life, and human use. Under climate change, inland water temperatures have increased and are expected to do so further, increasing the pressure on aquatic life and reducing the potential for human use. Here, future river water temperatures are projected for Switzerland based on a multi-fidelity modelling approach. We use 2 different, semi-empirical surface water temperature models, 22 coupled and downscaled general circulation- to regional climate models, future projections of river discharge from 4 hydrological models and 3 climate change scenarios (RCP2.6, 4.5, and 8.5). By grouping stream sections, catchments and spring-fed water courses under representative thermal regimes, and by employing hierarchical cluster-based thermal pattern recognition, an optimal model and model configuration was selected, model performance optimized and climate change impact assessment on river water temperatures improved. Results show that, until the end of the 21st century, average river water temperatures in Switzerland will likely increase by 3.1±0.7 °C (or 0.36±0.1 °C per decade) under RCP8.5, while under RCP2.6 the temperature increase may remain at 0.9±0.3 °C (0.12±0.1 °C per decade). Under RCP8.5, temperatures of rivers classified as being in the Alpine thermal regime will increase the most, that is, by 3.5±0.5 °C, followed by rivers of the Downstream Lake regime, 3.4±0.5 °C. A general decrease of river discharge in summer (-10 to -40 %) and increase in winter (+10 to +30 %), combined with a further increase in average near-surface air temperatures (0.5 °C per decade), bears the potential to not only result in overall warmer rivers, but also in prolonged periods of extreme summer river water temperatures. This dramatically increases the thermal stress potential for temperature sensitive aquatic species such as the brown trout in rivers where such periods occur already, but also rivers in where this previously was not a problem. By providing information of future water temperatures, the results of this study can guide managements climate mitigation efforts.

  • Open Access

    Reply on RC2

    by Love Raman Vinna, Vidushi Bigler, Oliver S. Schilling, Jannis Epting

    River water temperature is a key factor for water quality, aquatic life, and human use. Under climate change, inland water temperatures have increased and are expected to do so further, increasing the pressure on aquatic life and reducing the potential for human use. Here, future river water temperatures are projected for Switzerland based on a multi-fidelity modelling approach. We use 2 different, semi-empirical surface water temperature models, 22 coupled and downscaled general circulation- to regional climate models, future projections of river discharge from 4 hydrological models and 3 climate change scenarios (RCP2.6, 4.5, and 8.5). By grouping stream sections, catchments and spring-fed water courses under representative thermal regimes, and by employing hierarchical cluster-based thermal pattern recognition, an optimal model and model configuration was selected, model performance optimized and climate change impact assessment on river water temperatures improved. Results show that, until the end of the 21st century, average river water temperatures in Switzerland will likely increase by 3.1±0.7 °C (or 0.36±0.1 °C per decade) under RCP8.5, while under RCP2.6 the temperature increase may remain at 0.9±0.3 °C (0.12±0.1 °C per decade). Under RCP8.5, temperatures of rivers classified as being in the Alpine thermal regime will increase the most, that is, by 3.5±0.5 °C, followed by rivers of the Downstream Lake regime, 3.4±0.5 °C. A general decrease of river discharge in summer (-10 to -40 %) and increase in winter (+10 to +30 %), combined with a further increase in average near-surface air temperatures (0.5 °C per decade), bears the potential to not only result in overall warmer rivers, but also in prolonged periods of extreme summer river water temperatures. This dramatically increases the thermal stress potential for temperature sensitive aquatic species such as the brown trout in rivers where such periods occur already, but also rivers in where this previously was not a problem. By providing information of future water temperatures, the results of this study can guide managements climate mitigation efforts.

  • Open Access

    Comment on egusphere-2024-3957

    by Love Råman Vinnå, Vidushi Bigler, Oliver S. Schilling, Jannis Epting

    River water temperature is a key factor for water quality, aquatic life, and human use. Under climate change, inland water temperatures have increased and are expected to do so further, increasing the pressure on aquatic life and reducing the potential for human use. Here, future river water temperatures are projected for Switzerland based on a multi-fidelity modelling approach. We use 2 different, semi-empirical surface water temperature models, 22 coupled and downscaled general circulation- to regional climate models, future projections of river discharge from 4 hydrological models and 3 climate change scenarios (RCP2.6, 4.5, and 8.5). By grouping stream sections, catchments and spring-fed water courses under representative thermal regimes, and by employing hierarchical cluster-based thermal pattern recognition, an optimal model and model configuration was selected, model performance optimized and climate change impact assessment on river water temperatures improved. Results show that, until the end of the 21st century, average river water temperatures in Switzerland will likely increase by 3.1±0.7 °C (or 0.36±0.1 °C per decade) under RCP8.5, while under RCP2.6 the temperature increase may remain at 0.9±0.3 °C (0.12±0.1 °C per decade). Under RCP8.5, temperatures of rivers classified as being in the Alpine thermal regime will increase the most, that is, by 3.5±0.5 °C, followed by rivers of the Downstream Lake regime, 3.4±0.5 °C. A general decrease of river discharge in summer (-10 to -40 %) and increase in winter (+10 to +30 %), combined with a further increase in average near-surface air temperatures (0.5 °C per decade), bears the potential to not only result in overall warmer rivers, but also in prolonged periods of extreme summer river water temperatures. This dramatically increases the thermal stress potential for temperature sensitive aquatic species such as the brown trout in rivers where such periods occur already, but also rivers in where this previously was not a problem. By providing information of future water temperatures, the results of this study can guide managements climate mitigation efforts.