Fang Chen

Bio: Fang Chen is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Glacial lake & Glacial period. The author has an hindex of 15, co-authored 83 publications receiving 942 citations. Previous affiliations of Fang Chen include Beijing Normal University & Idaho State University.

Semantic Segmentation for High Spatial Resolution Remote Sensing Images Based on Convolution Neural Network and Pyramid Pooling Module

Abstract: Semantic segmentation provides a practical way to segment remotely sensed images into multiple ground objects simultaneously, which can be potentially applied to multiple remote sensed related aspects. Current classification algorithms in remotely sensed images are mostly limited by different imaging conditions, the multiple ground objects are difficult to be separated from each other due to high intraclass spectral variances and interclass spectral similarities. In this study, we propose an end-to-end framework to semantically segment high-resolution aerial images without postprocessing to refine the segmentation results. The framework provides a pixel-wise segmentation result, comprising convolutional neural network structure and pyramid pooling module, which aims to extract feature maps at multiple scales. The proposed model is applied to the ISPRS Vaihingen benchmark dataset from the ISPRS 2D Semantic Labeling Challenge. Its segmentation results are compared with previous state-of-the-art method UZ_1, UPB and three other methods that segment images into objects of all the classes (including clutter/background) based on true orthophoto tiles, and achieve the highest overall accuracy of 87.8% over the published performances, to the best of our knowledge. The results validate the efficiency of the proposed model in segmenting multiple ground objects from remotely sensed images simultaneously.

Scientific big data and Digital Earth

Abstract: Big data has been a focus of research in science, technology, economics, and social studies. Many countries have already incorporated big data research into their national strategies. This paper elaborates upon the origin, connotation, and development of big data from both a spatial and temporal perspective. It proposes that scientific big data will become a new solution in scientific research as the paradigm changes from being model-driven to data-driven. This paper defines the concept of “scientific big data” and proposes strategies for solving “big data problems”. Theoretical frameworks and data systems for Digital Earth are discussed with a clear conclusion that scientific big data is a prominent feature of Digital Earth. As an example, spatial cognition of the formation mechanism of China’s Heihe-Tengchong Line—a geo-demographic demarcation line dividing China into two parts—is discussed within the context of big data computation and analysis for Digital Earth.

Annual 30-meter Dataset for Glacial Lakes in High Mountain Asia from 2008 to 2017

Abstract: . Climate change is intensifying glacier melting and lake development in High Mountain Asia (HMA), which could increase glacial lake outburst flood hazards and impact water resource and hydroelectric power management. However, quantification of variability in size and type of glacial lakes at high resolution has been incomplete in HMA. Here, we developed a HMA Glacial Lake Inventory (Hi-MAG) database to characterize the annual coverage of glacial lakes from 2008 to 2017 at 30 m resolution using Landsat satellite imagery. It is noted that a rapid increase in lake number and moderate area expansion was influenced by a large population of small glacial lake (≤ 0.04 km2), and faster growth in lake number occurred above 5300 m elevation. Proglacial lake dominated areas showed significant lake area expansion, while unconnected lake dominated areas exhibited stability or slight reduction. Small glacial lakes accounted for approximately 15% of the lake area in Eastern Hindu Kush, Western Himalaya, Northern/Western Tien Shan, and Gangdise Mountains, but contributed > 50 % of lake area expansion in these regions over a decade. Our results demonstrate proglacial lakes are a main contributor while small glacial lakes are an overlooked element to recent lake evolution in HMA. Regional geographic variability of debris cover, together with trends in warming and precipitation over the past few decades, largely explain the current distribution of supra- and proglacial lake area across HMA. The Hi-MAG database are available at: https://doi.org/10.5281/zenodo.3700282 , it can be used for studies on glacier-climate-lake interactions, glacio-hydrologic models, glacial lake outburst floods and potential downstream risks and water resources.

Extraction of Glacial Lake Outlines in Tibet Plateau Using Landsat 8 Imagery and Google Earth Engine

Abstract: Glacial lake outburst floods (GLOFs) are among the most serious natural hazards in high mountain regions in the last several decades. The recent global warming has caused dramatic glacial lake changes and increased potential GLOF risk, particularly in Tibet Plateau (TP). Thus there is a pressing need to understand area and spatial distribution of glacial lakes at a large scale. Current efforts about glacial lake mapping in TP region is limited by spurious detections in the heterogeneous backgrounds. The nonlocal active contour algorithm, which takes full consideration of the regional heterogeneity in image, has been effectively applied in the field of medical image segmentation, but has not been tested at large scale of glaciated area yet. Moreover, the improved radiometric resolution and geographic coverage from Landsat 8 provides an opportunity to map glacial lakes. This study evaluated the potential of Landsat 8 images on annual glacial lake mapping in TP region which was characterized by various complex water conditions. The Google Earth Engine based cloud computing effectively facilitated the processing of a complete time series of Landsat 8 imagery from 2015 (156 path/rows and approximately 3580 scenes). Characteristics of glacial lake distribution were analyzed from aspects of size classes and elevation. Our results demonstrate that these strategies and methods automatically produce highly reliable glacial lake extents across the entire TP region, and are potentially applicable to other large-scale glacial lake mapping projects.

Drought-Induced Reduction in Global Terrestrial Net Primary Production from 2000 Through 2009

Abstract: Terrestrial net primary production (NPP) quantifies the amount of atmospheric carbon fixed by plants and accumulated as biomass. Previous studies have shown that climate constraints were relaxing with increasing temperature and solar radiation, allowing an upward trend in NPP from 1982 through 1999. The past decade (2000 to 2009) has been the warmest since instrumental measurements began, which could imply continued increases in NPP; however, our estimates suggest a reduction in the global NPP of 0.55 petagrams of carbon. Large-scale droughts have reduced regional NPP, and a drying trend in the Southern Hemisphere has decreased NPP in that area, counteracting the increased NPP over the Northern Hemisphere. A continued decline in NPP would not only weaken the terrestrial carbon sink, but it would also intensify future competition between food demand and proposed biofuel production.

Different glacier status with atmospheric circulations in Tibetan Plateau and surroundings

Abstract: Glacial melting in the Tibetan Plateau affects the water resources of millions of people. This study finds that—partly owing to changes in atmospheric circulations and precipitation patterns—the most intensive glacier shrinkage is in the Himalayan region, whereas glacial retreat in the Pamir Plateau region is less apparent.

Spectral mixture modeling - A new analysis of rock and soil types at the Viking Lander 1 site. [on Mars]

Abstract: A Viking Lander 1 image was modeled as mixtures of reflectance spectra of palagonite dust, gray andesitelike rock, and a coarse rocklike soil. The rocks are covered to varying degrees by dust but otherwise appear unweathered. Rocklike soil occurs as lag deposits in deflation zones around stones and on top of a drift and as a layer in a trench dug by the lander. This soil probably is derived from the rocks by wind abrasion and/or spallation. Dust is the major component of the soil and covers most of the surface. The dust is unrelated spectrally to the rock but is equivalent to the global-scale dust observed telescopically. A new method was developed to model a multispectral image as mixtures of end-member spectra and to compare image spectra directly with laboratory reference spectra. The method for the first time uses shade and secondary illumination effects as spectral end-members; thus the effects of topography and illumination on all scales can be isolated or removed. The image was calibrated absolutely from the laboratory spectra, in close agreement with direct calibrations. The method has broad applications to interpreting multispectral images, including satellite images.

Assessing the Impact

Abstract: This section offers suggestions related to helping a student deal with bullying in schools, as well as creating an environment where that individual can easily return to the school community. It also mentions the significance of the method 'Shared Responsibility' in dealing with the situation.