Search for: All records

Abstract In the wake of climate change, extreme events such as heatwaves are considered to be key players in the terrestrial biosphere. In the past decades, the frequency and severity of heatwaves have risen substantially, and they are projected to continue to intensify in the future. One key question is therefore: how do changes in extreme heatwaves affect the carbon cycle? Although soil respiration (Rs) is the second largest contributor to the carbon cycle, the impacts of heatwaves on Rs have not been fully understood. Using a unique set of continuous high frequency in-situ measurements from our field site, we characterize the relationship between Rs and heatwaves. We further compare the Rs response to heatwaves across ten additional sites spanning the contiguous United States (CONUS). Applying a probabilistic framework, we conclude that during heatwaves Rs rates increase significantly, on average, by ~ 26% relative to that of non-heatwave conditions over the CONUS. Since previous in-situ observations have not measured the Rs response to heatwaves (e.g., rate, amount) at the high frequency that we present here, the terrestrial feedback to the carbon cycle may be underestimated without capturing these high frequency extreme heatwave events. 

Urban air pollution is a public health challenge in low- and middle-income countries (LMICs). However, LMICs lack adequate air quality (AQ) monitoring infrastructure. A persistent challenge has been our inability to estimate AQ accurately in LMIC cities, which hinders emergency preparedness and risk mitigation. Deep learning-based models that map satellite imagery to AQ can be built for high-income countries (HICs) with adequate ground data. Here we demonstrate that a scalable approach that adapts deep transfer learning on satellite imagery for AQ can extract meaningful estimates and insights in LMIC cities based on spatiotemporal patterns learned in HIC cities. The approach is demonstrated for Accra in Ghana, Africa, with AQ patterns learned from two US cities, specifically Los Angeles and New York. 

Accurate and timely precipitation estimates are critical for monitoring and forecasting natural disasters such as floods. Despite having high-resolution satellite information, precipitation estimation from remotely sensed data still suffers from methodological limitations. State-of-the-art deep learning algorithms, renowned for their skill in learning accurate patterns within large and complex datasets, appear well suited to the task of precipitation estimation, given the ample amount of high-resolution satellite data. In this study, the effectiveness of applying convolutional neural networks (CNNs) together with the infrared (IR) and water vapor (WV) channels from geostationary satellites for estimating precipitation rate is explored. The proposed model performances are evaluated during summer 2012 and 2013 over central CONUS at the spatial resolution of 0.08° and at an hourly time scale. Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks (PERSIANN)–Cloud Classification System (CCS), which is an operational satellite-based product, and PERSIANN–Stacked Denoising Autoencoder (PERSIANN-SDAE) are employed as baseline models. Results demonstrate that the proposed model (PERSIANN-CNN) provides more accurate rainfall estimates compared to the baseline models at various temporal and spatial scales. Specifically, PERSIANN-CNN outperforms PERSIANN-CCS (and PERSIANN-SDAE) by 54% (and 23%) in the critical success index (CSI), demonstrating the detection skills of the model. Furthermore, the root-mean-square error (RMSE) of the rainfall estimates with respect to the National Centers for Environmental Prediction (NCEP) Stage IV gauge–radar data, for PERSIANN-CNN was lower than that of PERSIANN-CCS (PERSIANN-SDAE) by 37% (14%), showing the estimation accuracy of the proposed model.