Article
Environmental Sciences
Anca Dabija, Marcin Kluczek, Bogdan Zagajewski, Edwin Raczko, Marlena Kycko, Ahmed H. Al-Sulttani, Anna Tarda, Lydia Pineda, Jordi Corbera
Summary: Land cover information is crucial in European Union spatial management, with the development of the new version CLC+ in progress. Various methods and algorithms are being tested in Catalonia, Poland, and Romania to provide insights and guidance for development.
Article
Environmental Studies
Saleh Yousefi, Somayeh Mirzaee, Hussein Almohamad, Ahmed Abdullah Al Dughairi, Christopher Gomez, Narges Siamian, Mona Alrasheedi, Hazem Ghassan Abdo
Summary: This study aims to optimize the parameters of the support vector machine algorithm for generating land use/cover maps from Sentinel-2 satellite imagery in selected humid and arid climatic regions of Iran. The results show that the mapping accuracy for different climate types is sensitive to the penalty parameter, but variations of the gamma values in the kernel function have no effect on the accuracy of the maps.
Article
Environmental Sciences
Yoshie Ishii, Koki Iwao, Tsuguki Kinoshita
Summary: The study aimed to create a land cover map validation dataset with added spatial uniformity information using satellite images and DCP points, addressing the issue of using DCP points for accuracy assessment of global land cover maps. The new method devised in the study can guarantee the spatial uniformity of DCP validation data points at any resolution semi-automatically with a user's accuracy of 0.954, leading to differences in accuracy assessment trends across classes and regions for existing global land cover maps.
Article
Environmental Sciences
Padmanava Dash, Scott L. Sanders, Prem Parajuli, Ying Ouyang
Summary: The goal of this study is to improve the accuracy of land use and land cover (LULC) classification of satellite imagery for the Big Sunflower River Watershed, Mississippi using ancillary data, multiple classification methods, and a post-classification correction (PCC). The SVM classification method, combined with PCC, proved to be the most effective strategy for dealing with spectrally similar LULC features in both the growing season and post-harvest imagery. The strategies from this study can help evaluate LULC in agricultural and other watersheds.
Article
Environmental Sciences
Tesfaye Adugna, Wenbo Xu, Jinlong Fan
Summary: The type of algorithm used for remote sensing image classification has a significant impact on accuracy. In this paper, the performance of random forest (RF) and support vector machine (SVM) algorithms in large area land cover mapping using coarse-resolution images was compared. The results showed that RF outperformed SVM, especially in mixed class classification and handling large input datasets.
Article
Geography, Physical
Hamid Ebrahimy, Babak Mirbagheri, Ali Akbar Matkan, Mohsen Azadbakht
Summary: This study proposed a random forest-based approach for predicting per-pixel land cover accuracy of remote sensing images, showing good performance in various settings. The method establishes a nonlinear relationship between accuracy and spectral bands, and outperforms benchmark methods in all experimental sites.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2021)
Article
Environmental Sciences
Chenxi Li, Zaiying Ma, Liuyue Wang, Weijian Yu, Donglin Tan, Bingbo Gao, Quanlong Feng, Hao Guo, Yuanyuan Zhao
Summary: The study demonstrates that sampling strategies have significant impacts on land cover classification accuracy when the sample size is limited. The proposed object-oriented sampling approach is identified as one of the best strategies for collecting training samples, while stratified sampling and manual sampling perform well in specific situations.
Article
Environmental Sciences
Zhihao Wang, Alexander Brenning
Summary: Using active learning with uncertainty sampling can reduce the time and cost needed by experts under limited data conditions, improve model performance, and is particularly suitable for emergency response settings and landslide susceptibility modeling.
Article
Environmental Sciences
Zander S. Venter, Markus A. K. Sydenham
Summary: A 10 m resolution land cover map of Europe based on machine learning was proposed, achieving higher accuracy compared to other maps at the same resolution. Auxiliary data and spectro-temporal metrics significantly influenced the accuracy of the map.
Article
Computer Science, Artificial Intelligence
Xin Yan, Hongmiao Zhu
Summary: This paper proposes a novel support vector machine model with feature mapping and kernel trick to handle datasets with different distributions. The model improves robustness by pre-selecting training points, and converts the problem into a convex quadratic programming problem solved efficiently by the sequential minimal optimization algorithm. Numerical tests demonstrate the superior performance of the proposed method compared to other classification methods.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Geography, Physical
James Wickham, Stephen V. Stehman, Daniel G. Sorenson, Leila Gass, Jon A. Dewitz
Summary: The National Land Cover Database (NLCD), an operational land cover monitoring program, releases a land cover database every 2-3 years. The recent release, NLCD2019, extends the database to 18 years. A stratified random sample was used to collect land cover reference data for the 2016 and 2019 components of NLCD2019. The overall accuracies (OA) for land cover classification were evaluated and potential adjustments to improve map accuracy were discussed based on the analysis of map-reference agreement.
GISCIENCE & REMOTE SENSING
(2023)
Article
Environmental Sciences
James Wickham, Stephen Stehman, Daniel G. Sorenson, Leila Gass, Jon A. Dewitz
Summary: NLCD is an operational land cover monitoring program in the United States, with data collected every five years. The accuracy of land cover components in the NLCD2016 database was assessed using reference data for 2011 and 2016, showing overall accuracies around 72% for Level II and 79% for Level I components. The changes in mapping methodologies for NLCD2016 led to improved product quality compared to NLCD2011, with overall accuracies 4% to 7% higher.
REMOTE SENSING OF ENVIRONMENT
(2021)
Article
Green & Sustainable Science & Technology
Shravankumar Shivappa Masalvad, Chidanand Patil, Akkaram Pravalika, Basavaraj Katageri, Purandara Bekal, Prashant Patil, Nagraj Hegde, Uttam Kumar Sahoo, Praveen Kumar Sakare
Summary: The study examines the changes in land use and land cover in central Telangana districts using Landsat OLI datasets, TerrSet, and GIS tools. It predicts future changes and identifies areas of stress and accumulation. The research provides advice and a framework for urban planning and resource management.
ENVIRONMENT DEVELOPMENT AND SUSTAINABILITY
(2023)
Review
Environmental Studies
Chuanrong Zhang, Xinba Li
Summary: This article summarizes the research progress and applications of remote sensing, machine learning, deep learning, and geospatial big data in LULC mapping. The article identifies the opportunities and challenges in using geospatial big data for LULC mapping and suggests that more research is needed to improve the accuracy of large-scale LULC mapping.
Article
Environmental Sciences
Vineela Nandam, P. L. Patel
Summary: This study utilized Landsat images to map land use/land cover in a coastal urban floodplain, revealing that built-up and coastal-barren areas were the most confusing categories. New indices BCI and CBI were developed, and a hybrid approach MNDWI-CBI-SVM was used for mapping, achieving high accuracy.
GEOCARTO INTERNATIONAL
(2022)
Article
Geography, Physical
Brandon E. Cooper, Randel L. Dymond, Yang Shao
PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING
(2017)
Article
Geography, Physical
Carrie K. Jensen, Kevin J. McGuire, Yang Shao, C. Andrew Dollof
EARTH SURFACE PROCESSES AND LANDFORMS
(2018)
Article
Engineering, Electrical & Electronic
Gregory N. Taff, Yang Shao, Jie Ren, Ruoyu Zhang
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2018)
Article
Environmental Sciences
Erin E. Poor, Yang Shao, Marcella J. Kelly
JOURNAL OF ENVIRONMENTAL MANAGEMENT
(2019)
Article
Environmental Sciences
Hoa Thi Tran, James B. Campbell, Randolph H. Wynne, Yang Shao, Son Viet Phan
Article
Geography, Physical
Heng Wan, Yang Shao, James B. Campbell, Xinwei Deng
PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING
(2019)
Article
Environmental Sciences
Callie B. Lambert, Lynn M. Resleri, Yang Shao, David R. Butler
JOURNAL OF MOUNTAIN SCIENCE
(2020)
Article
Geography, Physical
Xiaoxiao Yan, Jing Li, Yang Shao, Zhenqi Hu, Zhen Yang, Shouqiang Yin, Ivyuan Cui
GISCIENCE & REMOTE SENSING
(2020)
Article
Biochemistry & Molecular Biology
D. J. Weiss, A. Nelson, C. A. Vargas-Ruiz, K. Gligoric, S. Bavadekar, E. Gabrilovich, A. Bertozzi-Villa, J. Rozier, H. S. Gibson, T. Shekel, C. Kamath, A. Lieber, K. Schulman, Y. Shao, V. Qarkaxhija, A. K. Nandi, S. H. Keddie, S. Rumisha, P. Amratia, R. Arambepola, E. G. Chestnutt, J. J. Millar, T. L. Symons, E. Cameron, K. E. Battle, S. Bhatt, P. W. Gething
Article
Environmental Sciences
John S. Iiames, Ellen Cooter, Andrew N. Pilant, Yang Shao
Article
Health Care Sciences & Services
Shreejana Bhattarai, Korine N. Kolivras, Kabita Ghimire, Yang Shao
Article
Environmental Sciences
Yang Shao, Austin J. Cooner, Stephen J. Walsh
Summary: This study demonstrates the potential of using two DCNNs (U-Net and VGG16) for high-resolution urban mapping, achieving good overall accuracy through OBIA methods and spatial testing. Further enhancement of mapping accuracy could be achieved with robust segmentation algorithms and improved quantity/quality of training samples.
Article
Geography, Physical
Jie Ren, Yang Shao, Heng Wan, Yanhua Xie, Adam Campos
Summary: This study mapped irrigated and non-irrigated corn at 30 m resolution for the state of Nebraska using a two-step multi-temporal image classification of MODIS and Landsat ARD. The proposed two-step analytical method has a high potential for automated annual irrigation mapping at 30 m spatial resolution, especially for the arid and semi-arid western U.S., providing clear field boundaries and irrigation frequency information.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2021)
Article
Ecology
Heng Wan, Daniel McLaughlin, Yang Shao, Brian van Eerden, Shyam Ranganathan, Xinwei Deng
Summary: Urban forests have higher evapotranspiration rates compared to other urban land covers, playing an important role in stormwater flood reduction. Wetland and upland forests have significantly higher ET rates than urban areas, with wetland forests contributing 40% of total landscape ET despite covering only 20% of the area.
LANDSCAPE AND URBAN PLANNING
(2021)
Article
Environmental Sciences
Allison Mitchell, Anamaria Bukvic, Yang Shao, Jennifer L. Irish, Daniel L. McLaughlin
Summary: The U.S. Mid-Atlantic coastal region, particularly Hampton Roads, Virginia, is experiencing higher rates of sea level rise (SLR) due to land subsidence. Current adaptation plans for coastal flooding are developed at the municipal level, lacking consideration of flooding beyond administrative boundaries. This study evaluates flooding impacts at the watershed scale in Hampton Roads, identifying at-risk areas and exploring the implications on municipalities, land uses, and land covers. The findings highlight the need for collaborative adaptation planning across hydrologically influenced spatial scales.
ENVIRONMENTAL MANAGEMENT
(2023)