A5014889794- Scientific Computing and Data Management
- Remote Sensing in Agriculture
- Distributed and Parallel Computing Systems
- Research Data Management Practices
- Air Quality Monitoring and Forecasting
- Smart Agriculture and AI
- Remote-Sensing Image Classification
- Data Management and Algorithms
- Service-Oriented Architecture and Web Services
- Advanced Computational Techniques and Applications
- Geographic Information Systems Studies
- Remote Sensing and Land Use
- Cryospheric studies and observations
- Hydrology and Drought Analysis
- Soil Moisture and Remote Sensing
- Environmental Monitoring and Data Management
- Image Retrieval and Classification Techniques
- Cloud Computing and Resource Management
- Geological Modeling and Analysis
- Climate variability and models
- Air Quality and Health Impacts
- Hydrology and Watershed Management Studies
- Atmospheric and Environmental Gas Dynamics
- Plant Water Relations and Carbon Dynamics
- IoT and Edge/Fog Computing
George Mason University
2016-2025
Nantong University
2024
Beijing Institute of Technology
2022
Wuhan University
2010-2013
State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing
2010-2012
Yield prediction is of great significance for yield mapping, crop market planning, insurance, and harvest management. Remote sensing becoming increasingly important in prediction. Based on remote data, progress has been made this field by using machine learning, especially the Deep Learning (DL) method, including Convolutional Neural Network (CNN) or Long Short-Term Memory (LSTM). Recent experiments area suggested that CNN can explore more spatial features LSTM ability to reveal phenological...
Abstract Risks associated with dust hazards are often underappreciated, a gap between the knowledge pool and public awareness that can be costly for impacted communities. This study reviews emission sources chemical, physical, biological characteristics of airborne soil particles (dust) their effects on human environmental health safety in Pan‐American region. American originates from both local (western United States, northern Mexico, Peru, Bolivia, Chile, Argentina) long‐range transport...
Recent trends within computational and data sciences show an increasing recognition adoption of workflows as tools for productivity reproducibility that also democratize access to platforms processing know-how. As digital objects be shared, discovered, reused, benefit from the FAIR principles, which stand Findable, Accessible, Interoperable, Reusable. The Workflows Community Initiative's Working Group (WCI-FW), a global open community researchers developers working with across disciplines...
Land cover maps are significant in assisting agricultural decision making. However, the existing workflow of producing land is very complicated and result accuracy ambiguous. This work builds a long short-term memory (LSTM) recurrent neural network (RNN) model to take advantage temporal pattern crops across image time series improve reduce complexity. An end-to-end framework proposed train test model. Landsat scenes used as Earth observations, some field-measured data together with CDL...
Accurate and timely estimation of crop yield at a small scale is great significance to food security harvest management. Recent studies have proven remote sensing an efficient method for machine learning, especially deep can infer good prediction by integrating multisource datasets such as satellite data, climate soil so on. However, there are some bottleneck challenges improve accuracy. First, the popular data used fall into two major groups-time-series constant data. Surprisingly little...
Recently, agricultural remote sensing community has endeavored to utilize the power of artificial intelligence (AI). One important topic is using AI make mapping crops more accurate, automatic, and rapid. This article proposed a classification workflow deep neural network (DNN) produce high-quality in-season crop maps from Landsat imageries for North Dakota. We use historical department Dakota ground measurements as training datasets. Processing workflows are created automate tedious...
Drought is one of the billion-dollar natural disasters and hard to trace measure. In recent years drought monitoring becomes much easier with remote sensing. However, it still difficult pin vegetation variances on because delay caused stress. To assess vegetative drought, important first understand relationship between meteorological condition condition, measure responses drought. It would be very helpful for effective early warning about agricultural This study uses CONUS as area, utilizes...
Recent advances in Web-related technologies have significantly promoted the wide sharing and integrated analysis of distributed geospatial data. Geospatial applications often involve diverse sources data complex geoprocessing functions. Existing Web-based GIS focuses more on access to In scientific problem solving, ability carry out is essential geoscientific discovery. This article presents design implementation GeoPW, a set services providing functions over Web. The concept Processing Web...
Accurate estimation of gross domestic product (GDP) at small geographies is great significance to evaluate the distribution and dynamics socio-economic development. Nighttime light (NTL) data becoming increasingly important in estimation. However, previous research has found that using NTL alone insufficient accurately measure GDP geographies, contribution for time-series unreliable. This article proposed a deep learning method Contiguous United States (CONUS) (2012-2015) county level. The...
There are two global aerosol forecast systems currently under development at NOAA, both of which coupled online with the Unified Forecast System (UFS), encompassing ocean, sea ice, wave and land surface components for Subseasonal to Seasonal (S2S) forecasting: UFS-Aerosols UFS-Chem.  The model is planned be implemented into Global Ensemble (GEFS) v13.0 in 2026, incorporates NASA’s 2nd-generation GOCART within a National Operational Prediction Capability (NUOPC)...
Land use and land cover (LULC) classification using satellite images is an important approach to monitor changes on earth. To produce LULC maps, supervised methods are often used. For many algorithms, independence of features implied assumption. However, this assumption rarely tested. classification, all bands as input models the default approach. some may be highly correlated, which cause model performances unstable. In research, correlations multicollinearity among multi-spectral analyzed...
Mountain snowpack provides critical water resources for forest and meadow ecosystems that are experiencing rapid change due to global warming. An accurate characterization of heterogeneity in these requires snow cover observations at high spatial resolutions, yet most existing datasets have a coarse resolution. To advance our observation capabilities meadows forests, we developed machine learning model generate snow-covered area (SCA) maps from PlanetScope imagery about 3-m The achieves...
It still remains a big challenge to accurately identify the geospatial objects with well-regulated outlines within remote sensing (RS) images such as residential buildings, factory storage highways, local roads, cars, and planes. In this paper, novel spatial feature index, which is named regular shape similarity index (RSSI), defined address challenge. represents ratio between area of an object its minimum bounding area. The application RSSI in identifying different shapes discussed,...
AI (artificial intelligence)-based analysis of geospatial data has gained a lot attention. Geospatial datasets are multi-dimensional; have spatiotemporal context; exist in disparate formats; and require sophisticated workflows that include not only the algorithm training testing, but also preprocessing result post-processing. This complexity poses huge challenge when it comes to full-stack workflow management, as researchers often use an assortment time-intensive manual operations manage...
Irrigation is the primary consumer of freshwater by humans and accounts for over 70% all annual water use. However, due to shortage open critical information in agriculture such as soil, precipitation, crop status, farmers heavily rely on empirical knowledge schedule irrigation tend excessive ensure yields. This paper presents WaterSmart-GIS, a web-based geographic system (GIS), collect disseminate near-real-time scheduling, soil moisture, evapotranspiration, humidity, stakeholders. The...
Effective and precise monitoring is a prerequisite to control human emissions slow disruptive climate change. To obtain the near-real-time status of power plant emissions, we built machine learning models trained them on satellite observations (Sentinel 5), ground observed data (EPA eGRID), meteorological (MERRA) directly predict NO2 emission rate coal-fired plants. A novel approach preprocessing multiple sources, coupled with neural network (RNN, LSTM), provided an automated way predicting...
Abstract The increasing prevalence of wearable devices has sparked a growing interest in real‐time health monitoring and physiological parameter tracking. This study focuses on the development cost‐effective sweat analysis device, utilizing microfluidic technology selective electrochemical electrodes for non‐invasive glucose potassium ions. through ion levels during physical activity, issues warning signal when reaching experimentally set thresholds (K+ concentration at 7.5 mM,...