Classification of Landscape Affected by Deforestation Using High-Resolution Remote Sensing Data and Deep-Learning Techniques

Human-induced deforestation has a major impact on forest ecosystems and therefore its detection and analysis methods should be improved. This study classified landscape affected by human-induced deforestation efficiently using high-resolution remote sensing and deep-learning. The SegNet and U-Net algorithms were selected for application with high-resolution remote sensing data obtained by the Kompsat-3 satellite. Land and forest cover maps were used as base data to construct accurate deep-learning datasets of deforested areas at high spatial resolution, and digital maps and a softwood database were used as reference data. Sites were classified into forest and non-forest areas, and a total of 13 areas (2 forest and 11 non-forest) were selected for analysis. Overall, U-Net was more accurate than SegNet (74.8% vs. 63.3%). The U-Net algorithm was about 11.5% more accurate than the SegNet algorithm, although SegNet performed better for the hardwood and bare land classes. The SegNet algorithm misclassified many forest areas, but no non-forest area. There was reduced accuracy of the U-Net algorithm due to misclassification among sub-items, but U-Net performed very well at the forest/non-forest area classification level, with 98.4% accuracy for forest areas and 88.5% for non-forest areas. Thus, deep-learning modeling has great potential for estimating human-induced deforestation in mountain areas. The findings of this study will contribute to more efficient monitoring of damaged mountain forests and the determination of policy priorities for mountain area restoration.

[1]  Bao-Jie He,et al.  An approach to examining performances of cool/hot sources in mitigating/enhancing land surface temperature under different temperature backgrounds based on landsat 8 image , 2019, Sustainable Cities and Society.

[2]  Raul Queiroz Feitosa,et al.  Applying Fully Convolutional Architectures for Semantic Segmentation of a Single Tree Species in Urban Environment on High Resolution UAV Optical Imagery , 2020, Sensors.

[3]  Patrick Bogaert,et al.  Forest change detection by statistical object-based method , 2006 .

[4]  P. Chavez.  Image-Based Atmospheric Corrections - Revisited and Improved , 1996 .

[5]  Lorenzo Bruzzone,et al.  Fusion of Hyperspectral and LIDAR Remote Sensing Data for Classification of Complex Forest Areas , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Yalçın Kuvan,et al.  Mass Tourism Development and Deforestation in Turkey , 2010 .

[7]  M. Herold,et al.  An assessment of deforestation and forest degradation drivers in developing countries , 2012 .

[8]  Qingming Zhan,et al.  Seasonal Variation of the Spatially Non-Stationary Association Between Land Surface Temperature and Urban Landscape , 2019, Remote. Sens..

[9]  José M. C. Pereira,et al.  Land-cover Mapping in the Brazilian Amazon Using SPOT-4 Vegetation Data and Machine Learning Classification Methods , 2006 .

[10]  Frédéric Achard,et al.  Forest classification of Southeast Asia using NOAA AVHRR data , 1995 .

[11]  João Paulo Papa,et al.  Efficient supervised optimum-path forest classification for large datasets , 2012, Pattern Recognit..

[12]  Amir Hossein Alavi,et al.  Machine learning in geosciences and remote sensing , 2016 .

[13]  Tian Wang,et al.  Classification of tree species and stock volume estimation in ground forest images using Deep Learning , 2019, Comput. Electron. Agric..

[14]  Wai Lok Woo,et al.  Temporal and spatial deep learning network for infrared thermal defect detection , 2019, NDT & E International.

[15]  Philippe Mayaux,et al.  Using remote sensing to inform conservation status assessment: Estimates of recent deforestation rates on New Britain and the impacts upon endemic birds , 2008 .

[16]  Miao Zhang,et al.  Land use mapping in the Three Gorges Reservoir Area based on semantic segmentation deep learning method , 2018, ArXiv.

[17]  Raul Queiroz Feitosa,et al.  EVALUATION OF DEEP LEARNING TECHNIQUES FOR DEFORESTATION DETECTION IN THE AMAZON FOREST , 2019, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences.

[18]  김래현,et al.  Valuation of Nonmarket Forest Resources , 2012 .

[19]  Rinku Roy Chowdhury,et al.  Driving forces of tropical deforestation: The role of remote sensing and spatial models , 2006 .

[20]  Peng Xie,et al.  A Local Land Use Competition Cellular Automata Model and Its Application , 2016, ISPRS Int. J. Geo Inf..

[21]  J. Estes,et al.  Using satellite remote sensing analysis to evaluate a socio-economic and ecological model of deforestation in Rondônia, Brazil , 1996 .

[22]  José García Rodríguez,et al.  A Review on Deep Learning Techniques Applied to Semantic Segmentation , 2017, ArXiv.

[23]  S. Myint,et al.  The Assessment of Deforestation, Forest Degradation, and Carbon Release in Myanmar 2000–2010 , 2019, Environmental Change in the Himalayan Region.

[24]  Eric F. Lambin,et al.  Impact of Macroeconomic Change on Deforestation in South Cameroon: Integration of Household Survey and Remotely-Sensed Data , 2000 .

[25]  Pankaj Bodani,et al.  Automatic building footprint extraction from very high-resolution imagery using deep learning techniques , 2020, Geocarto International.

[26]  D. Fuller,et al.  Tropical forest monitoring and remote sensing: A new era of transparency in forest governance? , 2006 .

[27]  Rui Li,et al.  Land Cover Classification from Remote Sensing Images Based on Multi-Scale Fully Convolutional Network , 2020, ArXiv.

[28]  Joanne C. White,et al.  Forest Monitoring Using Landsat Time Series Data: A Review , 2014 .

[29]  Yuanyong Dian,et al.  Comparing Fully Deep Convolutional Neural Networks for Land Cover Classification with High-Spatial-Resolution Gaofen-2 Images , 2020, ISPRS Int. J. Geo Inf..

[30]  P. Kareiva,et al.  Deforestation in Colombian protected areas increased during post-conflict periods , 2020, Scientific Reports.

[31]  Lelia Croitoru,et al.  Valuing the non-timber forest products in the Mediterranean region , 2007 .

[32]  Robert C. Harriss,et al.  Deforestation in Costa Rica: A Quantitative Analysis Using Remote Sensing Imagery 1 , 2001 .

[33]  Vivek Kumar Singh,et al.  An Efficient Solution for Breast Tumor Segmentation and Classification in Ultrasound Images Using Deep Adversarial Learning , 2019, ArXiv.

[34]  Jordi Inglada,et al.  Land Cover Maps Production with High Resolution Satellite Image Time Series and Convolutional Neural Networks: Adaptations and Limits for Operational Systems , 2019, Remote. Sens..

[35]  J. Im,et al.  Machine learning approaches for forest classification and change analysis using multi-temporal Landsat TM images over Huntington Wildlife Forest , 2013 .

[36]  Renato Fontes Guimarães,et al.  Change Detection of Deforestation in the Brazilian Amazon Using Landsat Data and Convolutional Neural Networks , 2020, Remote. Sens..

[37]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.