arXiv subjects

Auroop Ratan Ganguly

Publications and source records attributed to Auroop Ratan Ganguly.

4 recordsLinked to original sources

arXiv2026

MAUNet-Light: A Concise MAUNet Architecture for Bias Correction and Downscaling of Precipitation Estimates

Satellite-derived data products and climate model simulations of geophysical variables like precipitation, often exhibit systematic biases compared to in-situ measurements. Bias correction and spatial downscaling are fundamental components to develop operational weather forecast systems, as they seek to improve the consistency between coarse-resolution climate model simulations or satellite-based estimates and ground-based observations. In recent years, deep learning-based models have been increasingly replaced traditional statistical methods to generate high-resolution, bias free projections of climate variables. For example, Max-Average U-Net (MAUNet) architecture has been demonstrated for its ability to downscale precipitation estimates. The versatility and adaptability of these neural models make them highly effective across a range of applications, though this often come at the cost of high computational and memory requirements. The aim of this research is to develop light-weight neural network architectures for both bias correction and downscaling of precipitation, for which the teacher-student based learning paradigm is explored. This research demonstrates the adaptability of MAUNet to the task of bias correction, and further introduces a compact, lightweight neural network architecture termed MAUNet-Light.The proposed MAUNet-Light model is developed by transferring knowledge from the trained MAUNet, and it is designed to perform both downscaling and bias correction with reduced computational requirements without any significant loss in accuracy compared to state-of-the-art.

cs.LG↗

arXiv2019

Precipitation extremes and depth-duration-frequency under internal climate variability

Natural climate variability, captured through multiple initial condition ensembles, may be comparable to the variability caused by knowledge gaps in future emissions trajectories and in the physical science basis, especially at adaptation-relevant scales and projection horizons. The relations to chaos theory, including sensitivity to initial conditions, have caused the resulting variability in projections to be viewed as the irreducible uncertainty component of climate. The multiplier effect of ensembles from emissions-trajectories, multiple-models and initial-conditions contribute to the challenge. We show that ignoring this variability results in underestimation of precipitation extremes return periods leading to maladaptation. However, we show that concatenating initial-condition ensembles results in reduction of hydroclimate uncertainty. We show how this reduced uncertainty in precipitation extremes percolates to adaptation-relevant-Depth-Duration Frequency curves. Hence, generation of additional initial condition ensembles therefore no longer needs to be viewed as an uncertainty explosion problem but as a solution that can lead to uncertainty reduction in assessment of extremes.

stat.AP↗

arXiv2018

Generalized network recovery based on topology and optimization for real-world systems

Designing effective recovery strategies for damaged networked systems is critical to the resilience of built, human and natural systems. However, progress has been limited by the inability to bring together distinct philosophies, such as complex network topology through centrality measures and network flow optimization through entropy measures. Network centrality-based metrics are relatively more intuitive and computationally efficient while optimization-based approaches are more amenable to dynamic adjustments. Here we show, with case studies in real-world transportation systems, that the two distinct network philosophies can be blended to form a hybrid recovery strategy that is more effective than either, with the relative performance depending on aggregate network attributes. Direct applications include disaster management and climate adaptation sciences, where recovery of lifeline networks can save lives and economies.

physics.soc-ph↗

arXiv2018

Universal and generalizable restoration strategies for degraded ecological networks

Humans are increasingly stressing ecosystems via habitat destruction, climate change and global population movements leading to the widespread loss of biodiversity and the disruption of key ecological services. Ecosystems characterized primarily by mutualistic relationships between species such as plant-pollinator interactions may be particularly vulnerable to such perturbations because the loss of biodiversity can cause extinction cascades that can compromise the entire network. Here, we develop a general restoration strategy based on network-science for degraded ecosystems. Specifically, we show that network topology can be used to identify the optimal sequence of species reintroductions needed to maximize biodiversity gains following partial and full ecosystem collapse. This restoration strategy generalizes across topologically-disparate and geographically-distributed ecosystems. Additionally, we find that although higher connectance and diversity promote persistence in pristine ecosystems, these attributes reduce the effectiveness of restoration efforts in degraded networks. Hence, focusing on restoring the factors that promote persistence in pristine ecosystems may yield suboptimal recovery strategies for degraded ecosystems. Overall, our results have important insights for designing effective ecosystem restoration strategies to preserve biodiversity and ensure the delivery of critical natural services that fuel economic development, food security and human health around the globe

q-bio.PE↗