Jump to US Patents to see our Patents.


Using deep transfer learning and satellite imagery to estimate urban air quality in data-poor regions

Urban air pollution is a critical public health challenge in low-and-middle-income countries (LMICs). At the same time, LMICs tend to be data-poor, lacking adequate infrastructure to monitor air quality (AQ). As LMICs undergo rapid urbanization, the socio-economic burden of poor AQ will be immense. Here we present a globally scalable two-step deep learning (DL) based approach for AQ estimation in LMIC cities that mitigates the need for extensive AQ infrastructure on the ground. We train a DL model that can map satellite imagery to AQ in high-income countries (HICs) with sufficient ground data, and then adapt the model to learn meaningful AQ estimates in LMIC cities using transfer learning. The trained model can explain up to 54% of the variation in the AQ distribution of the target LMIC city without the need for target labels. The approach is demonstrated for Accra in Ghana, Africa, with AQ patterns learned and adapted from two HIC cities, specifically Los Angeles and New York.

Nishant Yadav, Meytar Sorek-Hamer, Michael Von Pohle, Ata Akbari Asanjan, Adwait Sahasrabhojanee, Esra Suel, Raphael E Arku, Violet Lingenfelter, Michael Brauer, Majid Ezzati, Nikunj Oza, Auroop R. Ganguly

2024 Feb 1

Explainable deep learning for insights in El Niño and river flows

The El Niño Southern Oscillation (ENSO) is a semi-periodic fluctuation in sea surface temperature (SST) over the tropical central and eastern Pacific Ocean that influences interannual variability in regional hydrology across the world through long-range dependence or teleconnections. Recent research has demonstrated the value of Deep Learning (DL) methods for improving ENSO prediction as well as Complex Networks (CN) for understanding teleconnections. However, gaps in predictive understanding of ENSO-driven river flows include the black box nature of DL, the use of simple ENSO indices to describe a complex phenomenon and translating DL-based ENSO predictions to river flow predictions. Here we show that eXplainable DL (XDL) methods, based on saliency maps, can extract interpretable predictive information contained in global SST and discover SST information regions and dependence structures relevant for river flows which, in tandem with climate network constructions, enable improved predictive understanding. Our results reveal additional information content in global SST beyond ENSO indices, develop understanding of how SSTs influence river flows, and generate improved river flow prediction, including uncertainty estimation. Observations, reanalysis data, and earth system model simulations are used to demonstrate the value of the XDL-CN based methods for future interannual and decadal scale climate projections.

Yumin Liu, Kate Duffy, Jennifer G. Dy & Auroop R. Ganguly

El Niño

Network-based restoration strategies maximize ecosystem recovery

Redressing global patterns of biodiversity loss requires quantitative frameworks that can predict ecosystem collapse and inform restoration strategies. By applying a network-based dynamical approach to synthetic and real-world mutualistic ecosystems, we show that biodiversity recovery following collapse is maximized when extirpated species are reintroduced based solely on their total number of connections in the original interaction network. More complex network-based strategies that prioritize the reintroduction of species that improve ‘higher order’ topological features such as compartmentalization do not provide meaningful performance improvements. These results suggest that it is possible to design nearly optimal restoration strategies that maximize biodiversity recovery for data-poor ecosystems in order to ensure the delivery of critical natural services that fuel economic development, food security, and human health around the globe.

Udit Bhatia, Sarth Dubey, Tarik C. Gouhier & Auroop R. Ganguly


Intensification and spatial homogenization of coastal upwelling under climate change

The timing and strength of wind-driven coastal upwelling along the eastern margins of major ocean basins regulate the productivity of critical fisheries and marine ecosystems by bringing deep and nutrient-rich waters to the sunlit surface, where photosynthesis can occur. How coastal upwelling regimes might change in a warming climate is therefore a question of vital importance. Although enhanced land–ocean differential heating due to greenhouse warming has been proposed to intensify coastal upwelling by strengthening alongshore winds, analyses of observations and previous climate models have provided little consensus on historical and projected trends in coastal upwelling. Here we show that there are strong and consistent changes in the timing, intensity and spatial heterogeneity of coastal upwelling in response to future warming in most Eastern Boundary Upwelling Systems (EBUSs). An ensemble of climate models shows that by the end of the twenty-first century the upwelling season will start earlier, end later and become more intense at high but not low latitudes. This projected increase in upwelling intensity and duration at high latitudes will result in a substantial reduction of the existing latitudinal variation in coastal upwelling. These patterns are consistent across three of the four EBUSs (Canary, Benguela and Humboldt, but not California). The lack of upwelling intensification and greater uncertainty associated with the California EBUS may reflect regional controls associated with the atmospheric response to climate change. Given the strong linkages between upwelling and marine ecosystems the projected changes in the intensity, timing and spatial structure of coastal upwelling may influence the geographical distribution of marine biodiversity.

Daiwei Wang, Tarik C. Gouhier, Bruce A. Menge & Auroop R. Ganguly


DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution

The impacts of climate change are felt by most critical systems, such as infrastructure, ecological systems, and power-plants. However,contemporary Earth System Models (ESM) are run at spatial resolutions too coarse for assessing effects this localized. Local scale projections can be obtained using statistical downscaling, a technique which uses historical climate observations to learn a low-resolution to high-resolution mapping. Depending on statistical modeling choices, downscaled projections have been shown to vary significantly terms of accuracy and reliability. The spatio-temporal nature of the climate system motivates the adaptation of super-resolution image processing techniques to statistical downscaling. In our work, we present DeepSD, a generalized stacked super resolution convolutional neural network (SRCNN) framework for statistical downscaling of climate variables. DeepSD augments SRCNN with multi-scale input channels to maximize predictability in statistical downscaling. We provide a comparison with Bias Correction Spatial Disaggregation as well as three Automated-Statistical Downscaling approaches in downscaling daily precipitation from 1 degree ( 100km) to 1/8 degrees ( 12.5km) over the Continental United States.Furthermore, a framework using the NASA Earth Exchange (NEX) platform is discussed for downscaling more than 20 ESM models with multiple emission scenarios.

Thomas Vandal, Evan Kodra, Sangram Ganguly, Andrew Michaelis, Ramakrishna Nemani, Auroop R Ganguly

ACM KDD 2017 Runner-up Best Paper Award Winner

Lack of uniform trends but increasing spatial variability in observed Indian rainfall extremes

Recent studies disagree on how rainfall extremes over India have changed in space and time over the past half century as well as on whether the changes observed are due to global warming or regional urbanization7. Although a uniform and consistent decrease in moderate rainfall has been reported a lack of agreement about trends in heavy rainfall may be due in part to differences in the characterization and spatial averaging of extremes. Here we use extreme value theory to examine trends in Indian rainfall over the past half century in the context of long-term, low-frequency variability. We show that when generalized extreme value theory is applied to annual maximum rainfall over India, no statistically significant spatially uniform trends are observed, in agreement with previous studies using different approaches. Furthermore, our space–time regression analysis of the return levels points to increasing spatial variability of rainfall extremes over India. Our findings highlight the need for systematic examination of global versus regional drivers of trends in Indian rainfall extremes, and may help to inform flood hazard preparedness and water resource management in the region.

Subimal Ghosh, Debasish Das, Shih-Chieh Kao , Auroop R. Ganguly

Nature Climate Change

Resilience of Urban Transport Network-of-Networks under Intense Flood Hazards Exacerbated by Targeted Attacks

Natural hazards including floods can trigger catastrophic failures in interdependent urban transport network-of-networks (NoNs). Population growth has enhanced transportation demand while urbanization and climate change have intensified urban floods. However, despite the clear need to develop actionable insights for improving the resilience of critical urban lifelines, the theory and methods remain underdeveloped. Furthermore, as infrastructure systems become more intelligent, security experts point to the growing threat of targeted cyber-physical attacks during natural hazards. Here we develop a hypothesis-driven resilience framework for urban transport NoNs, which we demonstrate on the London Rail Network (LRN). We find that topological attributes designed for maximizing efficiency rather than robustness render the network more vulnerable to compound natural-targeted disruptions including cascading failures. Our results suggest that an organizing principle for post-disruption recovery may be developed with network science principles. Our findings and frameworks can generalize to urban lifelines and more generally to real-world spatial networks.

Nishant Yadav, Samrat Chatterjee , Auroop R. Ganguly

Scientific Reports

Mapping crops within the growing season across the United States

Timely and accurate knowledge about the geospatial distribution of crops at regional to continental scales is crucial for forecasting crop production and estimating crop water use. The United States (US) is one of the leading food-producing countries, but lacks a nationwide high resolution crop-specific land cover map available publicly during the current growing season. The goal of this study was to map crops across the Continental US (CONUS) before the harvest, and to estimate the earliest date of classification by which crops can be mapped with sufficient accuracy (90% of full-season accuracy). The study employed a scalable cluster-then-label model that was trained on multiple years of MODIS NDVI using ground truth data in the form of US Department of Agriculture (USDA) Cropland Data Layer (CDL) products. The first step in the crop classification was to perform Multivariate Spatio-Temporal Clustering (MSTC) of annual MODIS-derived NDVI trajectories to create phenologically similar regions, or phenoregions. The second step was to assign crop labels to phenoregions based on spatial concordance between phenoregions and crop classes from CDL using Mapcurves. Assigning crop labels to phenoregions was performed within ecoregions to reduce classification errors due to spatial variability in phenology caused by variations in climate, agricultural practices, and growing conditions. The crop classifier was trained and validated on the years 2008–2014, then tested independently on 2015–2018. Ecoregion-level crop classification performed better than state-level and CONUS-level classification. Pixel-wise accuracy of classification for eight major crops by area was around 70% across the major corn-, soybeans- and winter wheatproducing areas, whereas regions characterized by high crop diversity had slightly lower accuracy. Classification accuracy for dominant crops like corn, soybeans, winter wheat, fallow/idle cropland and other hay/non alfalfa improved with time as they grew, reaching 90% of year-end accuracy by the end of August over each of the four unseen years in the test period. For corn and soybeans, the earliest dates of classification were found to be much earlier in the central regions of the Corn Belt (parts of Iowa, Illinois and Indiana) than in peripheral areas. The ability to map growing crops may permit near real-time monitoring of the health status and vigor of agricultural crops nationally.

Venkata Shashank Konduri,Jitendra Kumar, William W. Hargrove, Forrest M. Hoffman, Auroop R.Ganguly

Remote Sensing of Environment


For a full list of publications, visit the PI’s Google Scholar page here.

US Patents

  • US Patent on Climate Risk Analytics
    • Title: System for multivariable climate change forecasting with uncertainty quantification
    • US Patent Number: US Patent Number: 10488556
    • Inventors: Evan Kodra*, Auroop R. Ganguly
    • Assignee: Northeastern University, Boston, MA (NU News)
    • Date granted: November 26, 2019

  • US Patent on Infrastructure Network Resilience
    • Title: System for networking and analyzing geospatial data, human infrastructure, and natural elements
    • US Patent Number: US Patent Number: 10361907
    • Inventors: Udit Bhatia*, Devashish Kumar*, Evan Kodra*, Auroop R. Ganguly
    • Assignee: Northeastern University, Boston, MA (NU News)
    • Date granted: July 23, 2019