Engineering topics

Ramakrishna R. Nemani

Publications and source records attributed to Ramakrishna R. Nemani.

4 records

NASA NTRS2022

What Does Global Land Climate Look Like at 2°C Warming?

Constraining an increase in global mean temperature below 2°C compared to pre-industrial levels is critical to limiting dangerous and cascading impacts of anthropogenic climate change. Understanding future climatic changes and their spatial heterogeneity at 2°C warming is thus important for policy makers to prepare actionable adaptation and mitigation plans by identifying where and to what extent lives and livelihoods will be impacted. This study uses the recently released NASA Earth eXchange Global Daily Downscaled Projections (NEX-GDDP) CMIP6 data to provide a broad overview of projected changes in six key climate variables and two climate impact indicators at a time when warming exceeds 2°C. Analysis of global mean temperature changes indicates the 2040s as the decade when most CMIP6 models reach 2°C warming with respect to a pre-industrial period (1850–1900). During the 2040s, we find that global mean temperature, precipitation, relative humidity, downwelling shortwave and longwave radiation, and wind speed over land under the high emission scenario are projected to change by +2.8°C, +22.4 mm/year, −0.73%, −2.23 , +15.9 W/m 2 , and −0.04 m/s, respectively. Many of the future changes are expected to exacerbate climate impacts including heat stress and fire danger. Our analysis shows geographic patterns of policy-relevant climatic changes, as parts of the globe will experience significant climate impacts even if the goal to keep warming below 2°C goal is achieved. Our results highlight the urgent need for further studies focused on identifying key hotspots and advancing region-specific actionable adaptation and mitigation plans.

GDDP↗

NASA NTRS2022

Multisensor Machine Learning to Retrieve High Spatiotemporal Resolution Land Surface Temperature

Climate change is making heat waves more frequent, long-lasting, and severe. While multiple satellite types provide data to monitor surface temperature, geostationary (GEO) sensors provide near-continuous, continental-scale observations which can better capture the diurnal variability of land surface temperature (LST) than intermittent observations from low-earth orbit (LEO) sensors. However, standard products from GEO satellites are available at coarsened spatial and temporal resolutions compared to the native sensor resolution. Using datasets from the NASA Earth Exchange, we leveraged co-located, co-temporal observations from LEO and GEO satellites to learn a data-driven mapping using a convolutional neural network. The resulting NASA Earth eXchange Artificial Intelligence LST (NEXAI-LST) achieved a mean absolute error of 1.73 K relative to the target LEO product and improves on both spatial and temporal resolution [2 km, 10 minute] compared to the GEO full disk standard product [10 km, hourly]. In validation against measurements from a ground-based sensor network, NEXAI-LST achieves similar or better fit than both LEO and GEO standard products, while depending none of the prior knowledge of land surface and atmospheric states required by physical-statistical models. Further, application of the model to unseen LEO and GEO satellites demonstrates robust generalization of the model across spatial region, time of day, and sensor. In support of NASA’s open-source science initiative, we make our NEXAI-LST product, model, and codes available to facilitate data exploration and further studies.

Kate Marie Duffy↗

NASA NTRS2022

A Framework for Deep Learning Emulation of Numerical Models With a Case Study in Satellite Remote Sensing

Numerical models based on physics represent the state of the art in Earth system modeling and comprise our best tools for generating insights and predictions. Despite rapid growth in computational power, the perceived need for higher model resolutions overwhelms the latest generation computers, reducing the ability of modelers to generate simulations for understanding parameter sensitivities and characterizing variability and uncertainty. Thus, surrogate models are often developed to capture the essential attributes of the full-blown numerical models. Recent successes of machine learning methods, especially deep learning (DL), across many disciplines offer the possibility that complex nonlinear connectionist representations may be able to capture the underlying complex structures and nonlinear processes in Earth systems. A difficult test for DL-based emulation, which refers to function approximation of numerical models, is to understand whether they can be comparable to traditional forms of surrogate models in terms of computational efficiency while simultaneously reproducing model results in a credible manner. A DL emulation that passes this test may be expected to perform even better than simple models with respect to capturing complex processes and spatiotemporal dependencies. Here, we examine, with a case study in satellite-based remote sensing, the hypothesis that DL approaches can credibly represent the simulations from a surrogate model with comparable computational efficiency. Our results are encouraging in that the DL emulation reproduces the results with acceptable accuracy and often even faster performance. We discuss the broader implications of our results in light of the pace of improvements in high-performance implementations of DL and the growing desire for higher resolution simulations in the Earth sciences.

Bayesian Deep Learning↗

NASA NTRS2021

Spectral Synthesis for Geostationary Satellite-to-Satellite Translation

Earth-observing satellites carrying multispectral sensors are widely used to monitor the physical and biological states of the atmosphere, land, and oceans. These satellites have different vantage points above the Earth and different spectral imaging bands resulting in inconsistent imagery from one to another. This presents challenges in building downstream applications. What if we could generate synthetic bands for existing satellites from the union of all domains? We tackle the problem of generating synthetic spectral imagery for multispectral sensors as an unsupervised image-to-image translation problem modeled with a variational autoencoder (VAE) and generative adversarial network (GAN) architecture. Our approach introduces a novel shared spectral reconstruction loss to constrain the high-dimensional feature space of multispectral images. Simulated experiments performed by dropping one or more spectral bands show that cross-domain reconstruction outperforms measurements obtained from a second vantage point. Our proposed approach enables the synchronization of multispectral data and provides a basis for more homogeneous remote sensing datasets.

Geostationary satellites↗