Min Feng

Dr. Min Feng

Department of Geographical Sciences, University of Maryland, 4321 Hartwick Road STE 400, College Park, MD 20740, USA

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 October 2014 in International Journal of Digital Earth
Verified
Journal Article
Open access
MFMin Feng
Min Feng
JSJoseph O. Sexton
Joseph O. Sexton
SCSaurabh Channan
Saurabh Channan
JTJohn R. Townshend
John R. Townshend
The science and management of terrestrial ecosystems require accurate, high-resolution mapping of surface water. We produced a global, 30-m-resolution inland surface water dataset with an automated algorithm using Landsat-based surface reflectance estimates, multispectral water and vegetation indices, terrain metrics, and prior coarse-resolution water masks. The dataset identified 3,650,723 km2 of inland water globally – nearly three quarters of which was located in North America (40.65%) and Asia (32.77%), followed by Europe (9.64%), Africa (8.47%), South America (6.91%), and Oceania (1.57%). Boreal forests contained the largest portion of terrestrial surface water (25.03% of the global total), followed by the nominal ‘inland water’ biome (16.36%), tundra (15.67%), and temperate broadleaf and mixed forests (13.91%). Agreement with respect to the Moderate-resolution Imaging Spectroradiometer water mask and Landsat-based national land-cover datasets was very high, with commission errors <4% and omission errors <14% relative to each. Most of these were accounted for in the seasonality of water cover, snow and ice, and clouds – effects which were compounded by differences in image acquisition date relative to reference datasets. The Global Land Cover Facility (GLCF) inland surface water dataset is available for open access at the GLCF website (http://www.landcover.org).

2 May 2023 in Nature Reviews Earth & Environment
Verified
Journal Article
Closed access
PDF file
XLXin Li
Xin Li
MFMin Feng
Min Feng
Youhua RanYouhua Ran
Youhua Ran
YSYang Su
Yang Su
FLFeng Liu
Feng Liu
HGHuadong Guo
Huadong Guo

15 November 2019 in Remote Sensing
Verified
Journal Article
Open access
PDF file
HZHongwei Zhao
Hongwei Zhao
ZCZhongxin Chen
Zhongxin Chen
HJHao Jiang
Hao Jiang
Jing WenlongJing Wenlong
Jing Wenlong
Liang SunLiang Sun
Liang Sun
MFMin Feng
Min Feng
Timely and accurate estimation of the area and distribution of crops is vital for food security. Optical remote sensing has been a key technique for acquiring crop area and conditions on regional to global scales, but great challenges arise due to frequent cloudy days in southern China. This makes optical remote sensing images usually unavailable. Synthetic aperture radar (SAR) could bridge this gap since it is less affected by clouds. The recent availability of Sentinel-1A (S1A) SAR imagery with a 12-day revisit period at a high spatial resolution of about 10 m makes it possible to fully utilize phenological information to improve early crop classification. In deep learning methods, one-dimensional convolutional neural networks (1D CNNs), long short-term memory recurrent neural networks (LSTM RNNs), and gated recurrent unit RNNs (GRU RNNs) have been shown to efficiently extract temporal features for classification tasks. However, due to the complexity of training, these three deep learning methods have been less used in early crop classification. In this work, we attempted to combine them with an incremental classification method to avoid the need for training optimal architectures and hyper-parameters for data from each time series. First, we trained 1D CNNs, LSTM RNNs, and GRU RNNs based on the full images’ time series to attain three classifiers with optimal architectures and hyper-parameters. Then, starting at the first time point, we performed an incremental classification process to train each classifier using all of the previous data, and obtained a classification network with all parameter values (including the hyper-parameters) at each time point. Finally, test accuracies of each time point were assessed for each crop type to determine the optimal time series length. A case study was conducted in Suixi and Leizhou counties of Zhanjiang City, China. To verify the effectiveness of this method, we also implemented the classic random forest (RF) approach. The results were as follows: (i) 1D CNNs achieved the highest Kappa coefficient (0.942) of the four classifiers, and the highest value (0.934) in the GRU RNNs time series was attained earlier than with other classifiers; (ii) all three deep learning methods and the RF achieved F measures above 0.900 before the end of growth seasons of banana, eucalyptus, second-season paddy rice, and sugarcane; while, the 1D CNN classifier was the only one that could obtain an F-measure above 0.900 for pineapple before harvest. All results indicated the effectiveness of the solution combining the deep learning models with the incremental classification approach for early crop classification. This method is expected to provide new perspectives for early mapping of croplands in cloudy areas.

18 September 2014 in Remote Sensing
Verified
Journal Article
Open access
PDF file
YBYan Bai
Yan Bai
MFMin Feng
Min Feng
HJHao Jiang
Hao Jiang
JWJuanle Wang
Juanle Wang
Yunqiang ZhuYunqiang Zhu
Yunqiang Zhu
YLYingzhen Liu
Yingzhen Liu
Global land cover mapping with high accuracy is essential to downstream researches. Five global land cover data sets derived from moderate-resolution satellites, i.e., Global Land Cover Characterization (GLCC), University of Maryland land cover product (UMd), Global Land Cover 2000 project data (GLC2000), MODIS Land Cover product (MODIS LC), and GLOBCOVER land cover product (GlobCover), have been widely used in many researches. However, these data sets were produced using different data sources and class definitions, which led to high uncertainty and inconsistency when using them. This study looked into the consistencies and discrepancies among the five data sets in China. All of the compared data sets were aggregated to consistent spatial resolution and extent, along with a 12-class thematic classification schema; intercomparisons among five datasets and each with reference data GLCD-2005 were performed. Results show reasonable agreement across the five data sets over China in terms of the dominating land cover types like Grassland and Cropland; while discrepancies of Forest classes, particularly Shrubland and Wetland among them are great. Additionally, GLC2000 has the highest agreement with GLCD-2005; MODIS LC gets the highest map-specific consistency compared with others; whereas UMd has the lowest agreement with GLCD-2005, but also has the lowest map-specific consistency.

1 October 2016 in Remote Sensing of Environment
Verified
Journal Article
Open access
MFMin Feng
Min Feng
JSJoseph O. Sexton
Joseph O. Sexton
CHChengquan Huang
Chengquan Huang
AAAnupam Anand
Anupam Anand
SCSaurabh Channan
Saurabh Channan
JTJohn R. Townshend
John R. Townshend
The Global Land Cover Facility (GLCF) global forest-cover and -change dataset is a multi-temporal depiction of long-term (multi-decadal), global forest dynamics at high (30-m) resolution. Based on per-pixel estimates of percentage tree cover and their associated uncertainty, the dataset currently represents binary forest cover in nominal 1990, 2000, and 2005 epochs, as well as gains and losses over time. A comprehensive accuracy assessment of the GLCF dataset was performed using a global, design-based sample of 27,988 independent, visually interpreted reference points collected through a two-stage, stratified sampling design wherein experts visually identified forest cover and change in each of the 3 epochs based on Landsat and high-resolution satellite images, vegetation index profiles, and field photos. Consistent across epochs, the overall accuracy of the static forest-cover layers was 91%, and the overall accuracy of forest-cover change was >88% —among the highest accuracies reported for recent global forest- and land-cover data products. Both commission error (CE) and omission error (OE) were low for static forest cover in each epoch and for the stable classes between epochs (CE<3%, OE<22%), but errors were larger for forest loss (45%≤CE<62%, 47%

23 November 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
XZXuefei Zhang
Xuefei Zhang
MFMin Feng
Min Feng
HZHong Zhang
Hong Zhang
CWChao Wang
Chao Wang
YTYixian Tang
Yixian Tang
CWchunling wang
chunling wang
Rock glaciers represent typical periglacial landscapes and are distributed widely in alpine mountain environments. Rock glacier activity represents a critical indicator of water reserves state, permafrost distribution, and landslide disaster susceptibility. The dynamics of rock glacier activity in alpine periglacial environments are poorly quantified, especially in the central Himalayas. Multi-temporal Interferometric Synthetic Aperture Radar (MT-InSAR) has been shown to be a useful technique for rock glacier deformation detection. In this study, we developed a multi-baseline persistent scatterer (PS) and distributed scatterer (DS) combined MT-InSAR method to monitor the activity of rock glaciers in the central Himalayas. In periglacial landforms, the application of the PS interferometry (PSI) method is restricted by insufficient PS due to large temporal baseline intervals and temporal decorrelation, which hinder comprehensive measurements of rock glaciers. Thus, we first evaluated the rock glacier interferometric coherence of all possible interferometric combinations and determined a multi-baseline network based on rock glacier coherence; then, we constructed a Delaunay triangulation network (DTN) by exploiting both PS and DS points. To improve the robustness of deformation parameters estimation in the DTN, we combined the Nelder–Mead algorithm with the M-estimator method to estimate the deformation rate variation at the arcs of the DTN and introduced a ridge-estimator-based weighted least square (WLR) method for the inversion of the deformation rate from the deformation rate variation. We applied our method to Sentinel-1A ascending and descending geometry data (May 2018 to January 2019) and obtained measurements of rock glacier deformation for 4327 rock glaciers over the central Himalayas, at least more than 15% detecting with single geometry data. The line-of-sight (LOS) deformation of rock glaciers in the central Himalayas ranged from −150 mm to 150 mm. We classified the active deformation area (ADA) of all individual rock glaciers with the threshold determined by the standard deviation of the deformation map. The results show that 49% of the detected rock glaciers (monitoring rate greater than 30%) are highly active, with an ADA ratio greater than 10%. After projecting the LOS deformation to the steep slope direction and classifying the rock glacier activity following the IPA Action Group guideline, 12% of the identified rock glaciers were classified as active and 86% were classified as transitional. This research is the first multi-baseline, PS, and DS network-based MT-InSAR method applied to detecting large-scale rock glaciers activity.