6 research outputs found
Moving toward machine learning with distributed training data
No full textData accompanying paper titled: Moving toward machine learning with distributed training data
*Title and details subject to change in the near future. If you need to use this data immediately, please contact the author @ [email protected]
Recommended from our members
Incorporating Machine Learning with Satellite Data to Support Critical Infrastructure Measurement and Sustainable Development
No full textUnder the umbrella concept of Artificial Intelligence (AI) for good, recent advances in machine learning and large-scale data analysis have opened new opportunities to solve humanity’s most pressing challenges. Improvements in computation complexity and advances in AI (e.g., Vision Transformers) have led to faster and more effective techniques for extracting high-dimensional patterns from large-scale heterogeneous datasets (big data). Further, as satellite data become increasingly available at varying temporal-spatial resolutions, AI tools are helping us to better understand the underlying causes of environmental and socioeconomic changes at an unprecedented scale, ushering in an era of data-driven decision-making to support sustainable and equitable development. Based on these, we propose data-driven methods and techniques for critical infrastructure measurement and sustainable development. Using machine learning and remotely sensed data, we show that we can exploit knowledge and temporal-spatial characteristics learned from data-rich regions to improve data-driven predictions in regions with scant to no data. Specifically, we focus on three critical infrastructures: rivers, roads, and electricity access. Knowledge rivers, particularly their discharge, can help us understand how climate change is evolving, its manifestation on global water resources, and its impact on critical sectors like agriculture and renewable energy generation. On the other hand, better roads facilitate societal development, enabling access to local and global markets and socioeconomic opportunities, leading to better equality in service provision, faster socioeconomic development, and, ultimately, better human outcomes. Finally, we develop tools to support sustainable development, focusing on supporting electricity demand stimulation to improve energy access in rural communities. These methodologies and techniques can help emerging economies achieve their primary sustainable development goals (SDGs) by 2030.Electrical and Computer EngineeringDoctor of Philosophy (Ph.D.
A Framework for Estimating Global River Discharge From the Surface Water and Ocean Topography Satellite Mission
No full textInternational audienceThe Surface Water and Ocean Topography (SWOT) mission will vastly expand measurements of global rivers, providing critical new data sets for both gaged and ungaged basins. SWOT discharge products (available approximately 1 year after launch) will provide discharge for all river that reaches wider than 100 m. In this paper, we describe how SWOT discharge produced and archived by the US and French space agencies will be computed from measurements of river water surface elevation, width, and slope and ancillary data, along with expected discharge accuracy. We present for the first time a complete estimate of the SWOT discharge uncertainty budget, with separate terms for random (standard error) and systematic (bias) uncertainty components in river discharge time series. We expect that discharge uncertainty will be less than 30% for two-thirds of global reaches and will be dominated by bias. Separate river discharge estimates will combine both SWOT and in situ data; these “gage-constrained” discharge estimates can be expected to have lower systematic uncertainty. Temporal variations in river discharge time series will be dominated by random error and are expected to be estimated within 15% for nearly all reaches, allowing accurate inference of event flow dynamics globally, including in ungaged basins. We believe this level of accuracy lays the groundwork for SWOT to enable breakthroughs in global hydrologic science.Plain Language Summary The Surface Water and Ocean Topography (SWOT) satellite mission was launched on 15 December 2022. SWOT is designed to produce estimates of river discharge on many rivers where no in situ discharge measurements are currently available. This paper describes how SWOT discharge estimates will be created, and their expected accuracy. SWOT discharge will be estimated using simple flow laws that combine SWOT measurements of river water elevation above sea level, river width, and river slope, with ancillary data such as river bathymetry. We expect that discharge uncertainty will be less than 30% for two-thirds of global reaches and will be dominated by a systematic bias. Temporal variations in river discharge time series are expected to be estimated within 15% for nearly all reaches, thus capturing the response of river discharge to rainfall and snowmelt events, including in basins that are currently ungaged, and providing a new capability for scientists to better track the flows of freshwater water through the Earth system
A First Look at River Discharge Estimation From SWOT Satellite Observations
No full textAbstract The Surface Water and Ocean Topography (SWOT) satellite has the potential to transform global hydrologic science by offering simultaneous and synoptic estimates of river discharge and other hydraulic variables. Discharge is estimated from SWOT observations of water surface elevation, width, and slope. A first assessment using just the highest quality SWOT measurements, over the first 15 months (March 2023–July 2024) of the mission evaluated at 65 gauged reaches shows results consistent with pre‐launch expectations. SWOT estimates track discharge dynamics without relying on any gauge information: median correlation is 0.73, with a correlation interquartile range of 0.51–0.89. SWOT estimates capture discharge magnitude correctly in some cases but are biased (median bias is 50%) in others. There are already a total of 11,274 ungauged global locations with highest quality SWOT measurements where SWOT discharge is expected to accurately track discharge variations: this value will increase as SWOT data record length grows, algorithms are refined and SWOT measurements are reprocessed. This first look indicates that SWOT discharge is performing as expected for SWOT data that achieve performance requirements, providing observed information on discharge variations in ungauged basins globally
