About

Professor Yang Shao is associated with the Center for Geospatial Information Technology (CGIT) at Virginia Tech, which collaborates across research, education, and outreach with a transdisciplinary approach to address complex problems using geospatial science. The center focuses on applying geospatial science to improve quality of life, environment, and community through smart decision making, utilizing extensive knowledge in Geographic Information Systems (GIS) to develop powerful, user-friendly geospatial tools. CGIT's work involves transforming spatial data into secure, intuitive decision-making tools that empower agencies, researchers, and communities across the Commonwealth of Virginia, with applications ranging from highway safety and crash analysis to statewide broadband and environmental initiatives.

Research topics

• Computer Science
• Geography
• Artificial Intelligence
• Medicine
• Ecology
• Biology
• Economic growth
• Environmental health
• Business
• Archaeology
• Radiology
• Remote sensing
• Forestry
• Physical geography

Selected publications

• A Novel Landsat-Derived Multispectral Index for Coal Dust Detection: Spatiotemporal Dispersion Patterns and Natural Driving Forces

  IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · 2025-01-01 · 3 citations

  articleOpen access

  Coal dust pollution, a major byproduct of mining, poses significant environmental and health risks. However, the temporal diffusion and spatial extent of coal dust remain unclear, complicating ecological restoration efforts and intensifying conflicts between mining and human settlements. This study develops a Mining-Environment Coal Dust Index (MECDI) using Landsat imagery (1989-2022) to monitor coal dust in the Baorixile coalfield, Inner Mongolia, enhancing detection accuracy. Fluent simulations analyzed the influence of meteorological and topographic factors on dust dispersion. Results indicate that coal dust spreads beyond the mining zones, with significant reductions since 2019 due to control measures. In open-pit mines, coal dust follows a “right-skewed” patterns over time. In underground mine area, dust diffusion increased until 2017, then stabilized, follows a logistic curve in “S” shape. The highest dust concentrations were within 800 m of the mining area and along transportation routes. Coal dust accumulation is more affected by slope degree than aspect, with lower slopes more prone to dust buildup. High wind speeds and greater pressure differences facilitate dust dispersion, while low wind speeds and circulation patterns contribute to dust accumulation at the pit bottom. The proposed MECDI index introduces an innovative and scalable metric for coal dust pollution monitoring, enabling more precise assessments and informed mitigation strategies that support sustainable mining and regional environmental governance.

  PublisherDOI

• Land Cover Mapping in East China for Enhancing High-Resolution Weather Simulation Models

  Remote Sensing · 2024-10-10 · 1 citations

  articleOpen access

  This study was designed to develop a 30 m resolution land cover dataset to improve the performance of regional weather forecasting models in East China. A 10-class land cover mapping scheme was established, reflecting East China’s diverse landscape characteristics and incorporating a new category for plastic greenhouses. Plastic greenhouses are key to understanding surface heterogeneity in agricultural regions, as they can significantly impact local climate conditions, such as heat flux and evapotranspiration, yet they are often not represented in conventional land cover classifications. This is mainly due to the lack of high-resolution datasets capable of detecting these small yet impactful features. For the six-province study area, we selected and processed Landsat 8 imagery from 2015–2018, filtering for cloud cover. Complementary datasets, such as digital elevation models (DEM) and nighttime lighting data, were integrated to enrich the inputs for the Random Forest classification. A comprehensive training dataset was compiled to support Random Forest training and classification accuracy. We developed an automated workflow to manage the data processing, including satellite image selection, preprocessing, classification, and image mosaicking, thereby ensuring the system’s practicality and facilitating future updates. We included three Weather Research and Forecasting (WRF) model experiments in this study to highlight the impact of our land cover maps on daytime and nighttime temperature predictions. The resulting regional land cover dataset achieved an overall accuracy of 83.2% and a Kappa coefficient of 0.81. These accuracy statistics are higher than existing national and global datasets. The model results suggest that the newly developed land cover, combined with a mosaic option in the Unified Noah scheme in WRF, provided the best overall performance for both daytime and nighttime temperature predictions. In addition to supporting the WRF model, our land cover map products, with a planned 3–5-year update schedule, could serve as a valuable data source for ecological assessments in the East China region, informing environmental policy and promoting sustainability.

  PublisherOA PDFDOI

• Annual Cropping Intensity Dynamics in China from 2001 to 2023

  Remote Sensing · 2024-12-23 · 1 citations

  articleOpen access

  Spatial and temporal information about cropping patterns of single and multiple crops is important for monitoring crop production and land-use intensity. We used time-series MODIS NDVI 8-day composite data to develop annual cropping pattern products at a 250 m spatial resolution for China, covering the period from 2001 to 2023. To address the potential impacts of varying parameters in both data pre-processing and the peak detection algorithm on the accuracy of cropping pattern mapping, we employed a grid-search method to fine-tune these parameters. This process focused on optimizing the Savitzky–Golay smoothing window size and the peak width parameters using a calibration dataset. The results highlighted that an optimal combination of a five to seven MODIS composite window size in Savitzky–Golay smoothing and a peak width of four MODIS composites achieved good overall mapping accuracy. Pixel-wise accuracy assessments were conducted for the selected mapping years of 2001, 2011, and 2021. Overall accuracies were between 89.7% and 92.0%, with F1 scores ranging from 0.921 to 0.943. Nationally, this study observed a fluctuating trend in multiple cropping percentages, with a notable increase after 2013, suggesting shifts toward more intensive agricultural practices in recent years. At a finer spatial scale, the combination of Mann–Kendall and Sen’s slope analyses revealed that approximately 12.9% of 3 km analytical windows exhibited significant changes in cropping intensity. We observed spatial clusters of increasing and decreasing crop intensity trends across provinces such as Hebei, Shandong, Shaanxi, and Gansu. This study underscores the importance of data smoothing and peak detection methods in analyzing high temporal resolution remote sensing data. The generation of annual single/multiple cropping pattern maps at a 250 m spatial resolution enhances our comprehension of agricultural dynamics through time and across different regions.

  PublisherOA PDFDOI

• Virtual elastography ultrasound via generative adversarial network for breast cancer diagnosis

  Nature Communications · 2023 · 49 citations

  • Computer Science
  • Artificial Intelligence
  • Computer Science

  Elastography ultrasound (EUS) imaging is a vital ultrasound imaging modality. The current use of EUS faces many challenges, such as vulnerability to subjective manipulation, echo signal attenuation, and unknown risks of elastic pressure in certain delicate tissues. The hardware requirement of EUS also hinders the trend of miniaturization of ultrasound equipment. Here we show a cost-efficient solution by designing a deep neural network to synthesize virtual EUS (V-EUS) from conventional B-mode images. A total of 4580 breast tumor cases were collected from 15 medical centers, including a main cohort with 2501 cases for model establishment, an external dataset with 1730 cases and a portable dataset with 349 cases for testing. In the task of differentiating benign and malignant breast tumors, there is no significant difference between V-EUS and real EUS on high-end ultrasound, while the diagnostic performance of pocket-sized ultrasound can be improved by about 5% after V-EUS is equipped.

  PublisherOA PDFDOI

• Evaluation of predicted loss of different land use and land cover (LULC) due to coastal erosion in Bangladesh

  Frontiers in Environmental Science · 2023-04-19 · 20 citations

  articleOpen accessSenior author

  Coastal erosion is one of the most significant environmental threats to coastal communities globally. In Bangladesh, coastal erosion is a regularly occurring and major destructive process, impacting both human and ecological systems at sea level. The Lower Meghna estuary, located in southern Bangladesh, is among the most vulnerable landscapes in the world to the impacts of coastal erosion. Erosion causes population displacement, loss of productive land area, loss of infrastructure and communication systems, and, most importantly, household livelihoods. With an aim to assess the impacts of historical and predicted shoreline change on different land use and land cover, this study estimated historical shoreline movement, predicted shoreline positions based on historical data, and quantified and assessed past land use and land cover change. Multi-temporal Landsat images from 1988–2021 were used to quantify historical shoreline movement and past land use and land cover. A time-series classification of historical land use and land cover (LULC) were produced to both quantify LULC change and to evaluate the utility of the future shoreline predictions for calculating amounts of lost or newly added land resources by LULC type. Our results suggest that the agricultural land is the most dominant land cover/use (76.04% of the total land loss) lost over the studied period. Our results concluded that the best performed model for predicting land loss was the 10-year time depth and 20-year time horizon model. The 10-year time depth and 20-year time horizon model was also most accurate for agricultural, forested, and inland waterbody land use/covers loss prediction. We strongly believe that our results will build a foundation for future research studying the dynamics of coastal and deltaic environments.

  PublisherOA PDFDOI

• Cytokine-driven positive feedback loop organizes fibroblast transformation and facilitates gastric cancer progression

  Clinical & Translational Oncology · 2022-03-18 · 8 citations

  article
  PublisherDOI

• Comprehensive Risk System Based on Shear Wave Elastography and BI-RADS Categories in Assessing Axillary Lymph Node Metastasis of Invasive Breast Cancer—A Multicenter Study

  Frontiers in Oncology · 2022-03-10 · 17 citations

  articleOpen access

  Purpose To develop a risk stratification system that can predict axillary lymph node (LN) metastasis in invasive breast cancer based on the combination of shear wave elastography (SWE) and conventional ultrasound. Materials and Methods A total of 619 participants pathologically diagnosed with invasive breast cancer underwent breast ultrasound examinations were recruited from a multicenter of 17 hospitals in China from August 2016 to August 2017. Conventional ultrasound and SWE features were compared between positive and negative LN metastasis groups. The regression equation, the weighting, and the counting methods were used to predict axillary LN metastasis. The sensitivity, specificity, and the areas under the receiver operating characteristic curve (AUC) were calculated. Results A significant difference was found in the Breast Imaging Reporting and Data System (BI-RADS) category, the “stiff rim” sign, minimum elastic modulus of the internal tumor and peritumor region of 3 mm between positive and negative LN groups ( p < 0.05 for all). There was no significant difference in the diagnostic performance of the regression equation, the weighting, and the counting methods (p > 0.05 for all). Using the counting method, a 0–4 grade risk stratification system based on the four characteristics was established, which yielded an AUC of 0.656 (95% CI, 0.617–0.693, p < 0.001), a sensitivity of 54.60% (95% CI, 46.9%–62.1%), and a specificity of 68.99% (95% CI, 64.5%–73.3%) in predicting axillary LN metastasis. Conclusion A 0–4 grade risk stratification system was developed based on SWE characteristics and BI-RADS categories, and this system has the potential to predict axillary LN metastases in invasive breast cancer.

  PublisherOA PDFDOI

• Remotely-sensed evapotranspiration for informed urban forest management

  Landscape and Urban Planning · 2021-03-12 · 15 citations

  article
  PublisherDOI

• Driving forces of grassland vegetation changes in Chen Barag Banner, Inner Mongolia

  GIScience & Remote Sensing · 2020 · 49 citations

  • Geography
  • Physical geography
  • Forestry

  Inner Mongolia is an important ecological zone of northern China and 67% of its land area is grassland. This ecologically fragile region has experienced significant vegetation degradation during the last decades. Although the spatial extents and rates of vegetation change have previously been characterized through various remote sensing and GIS studies, the underlying driving factors of vegetation changes are still not well understood. In this study, we first used time-series MODIS NDVI data from 2000 to 2016 to characterize the temporal trend of vegetation changes. These vegetation change trends were compared with climate and socioeconomic variables to determine the potential drivers. We used a set of statistical methods, including multiple linear regression (MLR), spatial correlation analysis, and partial least squares (PLS) regression analyzes, to quantify the spatial distribution of the driving forces and their relative importance to vegetation changes. Results show that the main driving factors and their impact magnitude (weight) are in the order of human activities (r = -0.785, p < 0.01, VIP = 1.37), precipitation (r = 0.541, p < 0.05, VIP = 0.89), temperature (r = -0.319, p > 0.05 VIP = 0.59). The area affected by human activities was 10.57%. Specific human activities, such as coal mining and grazing were negatively associated with vegetation cover, while eco-engineering projects had positive impacts. This study provided thorough quantification of driving forces of vegetation change and enhanced our understanding of their interactions. Our integrated geospatial-statistical approach is particularly important for sustainable development of ecosystem balance in Chen Barag Banner and other areas facing similar challenges.

  PublisherDOI

• Land cover and land use change in an emerging national park gateway region: implications for mountain sustainability

  Edward Elgar Publishing eBooks · 2020-05-07 · 4 citations

  book-chapterOpen access

  Land cover and land use change (LCLUC) refers to conversion of natural and human-dominated landscapes through human processes. Because LCLUC encompasses both human and environmental systems, with their interactions and feedback from local to global scales, the study of LCLUC now forms a cornerstone of sustainability research. Within the United States, mountain landscapes share complex relationships with land cover change processes. Given that a large portion of US mountain landscapes are designated as public lands, mountainous regions are distinctive for their physical and cultural amenities, and mountains are vulnerable landscapes. Combined, these forces and their interactions have important implications for outcomes of LCLUC on mountain sustainability. Here, we conducted a decadal LCLUC analysis to examine the nature and trajectory of LCLUC within Glacier National Park (GNP), Montana, a designated mountain Biosphere Reserve and a UNESCO World Heritage Site, and the two bordering counties—Glacier and Flathead. GNP has been recognized as among the most threatened parks in the United States, given surrounding development activities and competing land uses that are pressuring terrestrial and aquatic ecological diversity. We were especially interested in forest and agricultural land change, and growth of urban land cover. For our study area and for the following time periods: 1991–2001, 2001–2011, and 1991–2011, our specific objectives were to: (1) quantify changes in amount, and assess spatial organization of, impervious surface cover; and (2) quantify changes in amount, and assess spatial organization of, forest and agricultural cover. To support the decadal LCLUC analysis we examined urban-related changes for the study area using impervious surface mapping. Forested area and agricultural lands were characterized using the 2001 NLCD, 2011 NLCD, and 1992/2001 NLCD Retrofit Products. Initial land cover classes were recoded to forest, agricultural land, urban, and other. We used four pattern metrics to categorize spatial organization: Percentage of Landscape (PLAND), Largest Patch Index (LPI), Mean Patch Size (MPS), and Patch Size. Areas surrounding GNP have been experiencing an increase in exurban development and an increase in forest fragmentation, but these results are spatially and temporally variable between the east and west bordering counties. For the entire study area, total impervious surfaces increased from 35.24 km2 in 1991 to 45.90 km2 in 2011, corresponding to a 30.30 percent increase. More urban development occurred from 1991 to 2001 than from 2001 to 2011. Annual increase rate was ~ 1.90 percent and 0.95 percent for 1992–2001 and 2001–2011, respectively. For the entire study period from 1991 to 2011, we observed similar rates (-8.81 to -9.94 percent) of forest loss between the two counties of analysis. The majority of forest loss occurred in the most recent decade. Agricultural lands also decreased from 1991 to 2001, although at relatively slower rates. Unprotected mountainous landscapes that are not part of the Blackfeet Indian Reservation have shown pronounced change in exurban development, as shown through impervious cover mapping. This work indicates that while the GNP gateway region may still be comparatively rural, GNP is not isolated from urbanization. Thus, the concept of ‘protected’ mountainous regions is challenged.

  PublisherOA PDFDOI

Frequent coauthors

• James B. Campbell

  13 shared

• LiYing Shi

  Affiliated Hospital of Guizhou Medical University

  8 shared

• Yanjun Xu

  8 shared

• Jinping Liu

  Hunan Normal University

  8 shared

• Ligang Cui

  Peking University

  8 shared

• Qiongchao Jiang

  Sun Yat-sen Memorial Hospital

  8 shared

• Hong-Ju Yan

  Hangzhou First People's Hospital

  8 shared

• Ping Zhou

  Shaoxing People's Hospital

  8 shared

Labs

• Center for Geospatial Information TechnologyPI

  N/A

Awards & honors

• Physically Informed, Equitable, & Efficient Hurricane Surge…
• Harmful Algal Bloom (HAB) Study for Smith Mountain Lake (202…
• Mapping school bus depots of the U.S. using machine learning…
• Flood Reduction Potential of Urban Forests in Virginia Beach…
• Conserving Urban Forests to Reduce Flooding (2020-2023)