Monitoring Oil Exploitation Infrastructure and Dirt Roads with Object-Based Image Analysis and Random Forest in the Eastern Mongolian Steppe

Information on the spatial distribution of human disturbance is important for assessing and monitoring land degradation. In the Eastern Mongolian Steppe Ecosystem, one of the major driving factors of human-induced land degradation is the expansion of road networks mainly due to intensifications of oil exploration and exploitation. So far, neither the extents of road networks nor the extent of surrounding grasslands affected by the oil industry are monitored which is generally labor consuming. This causes that no information on the changes in the area which is affected by those disturbance drivers is available. Consequently, the study aim is to provide a cost-effective methodology to classify infrastructure and oil exploitation areas from remotely sensed images using object-based classifications with Random Forest. By combining satellite data with different spatial and spectral resolutions (PlanetScope, RapidEye, and Landsat ETM+), the product delivers data since 2005. For the classification variables, segmentation, spectral characteristics, and indices were extracted from all above mentioned imagery and used as predictors. Results show that overall accuracies of land use maps ranged 73%–93% mainly depending on satellites’ spatial resolution. Since 2005, the area of grassland disturbed by dirt roads and oil exploitation infrastructure increased by 88% with its highest expansion by 47% in the period 2005–2010. Settlements and croplands remained relatively constant throughout the 13 years. Comparison of multiscale classification suggests that, although high spatial resolutions are clearly beneficial, all datasets were useful to delineate linear features such as roads. Consequently, the results of this study provide an effective evaluation for the potential of Random Forest for extracting relatively narrow linear features such as roads from multiscale satellite images and map products that are possible to use for detailed land degradation assessments.

[1]  Peijun Du,et al.  A review of supervised object-based land-cover image classification , 2017 .

[2]  N. Tsendbazar,et al.  The Environmental Impact of not Having Paved Roads in Arid Regions: An Example from Mongolia , 2012, AMBIO.

[3]  A. Huete A soil-adjusted vegetation index (SAVI) , 1988 .

[4]  Holly K. Gibbs,et al.  Mapping the world's degraded lands , 2015 .

[5]  Zhaohua Chen,et al.  Well site extraction from Landsat-5 TM imagery using an object- and pixel-based image analysis method , 2014 .

[6]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[7]  Ksenya V. Mjachina,et al.  Detection of damaged areas caused by the oil extraction in a steppe region using winter landsat imagery , 2018 .

[8]  Krištof Oštir,et al.  Investigating the impact of spatial and spectral resolution of satellite images on segmentation quality , 2014 .

[9]  Jacob Cohen A Coefficient of Agreement for Nominal Scales , 1960 .

[10]  C. Justice,et al.  The Harmonized Landsat and Sentinel-2 surface reflectance data set , 2018, Remote Sensing of Environment.

[11]  Thomas Blaschke,et al.  Object based image analysis for remote sensing , 2010 .

[12]  Chris W. Baynard Remote Sensing Applications: Beyond Land-Use and Land-Cover Change , 2013 .

[13]  Yizong Cheng,et al.  Mean Shift, Mode Seeking, and Clustering , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Weicheng Wu,et al.  Assessing woody biomass in African tropical savannahs by multiscale remote sensing , 2013 .

[15]  G. H. Rosenfield,et al.  A coefficient of agreement as a measure of thematic classification accuracy. , 1986 .

[16]  Ross K. Meentemeyer,et al.  Comparing Quantity, Allocation and Configuration Accuracy of Multiple Land Change Models , 2017 .

[17]  R. Pontius,et al.  Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment , 2011 .

[18]  Laurence C. Smith,et al.  Tracking Dynamic Northern Surface Water Changes with High-Frequency Planet CubeSat Imagery , 2017, Remote. Sens..

[19]  Clement Atzberger,et al.  Self-Guided Segmentation and Classification of Multi-Temporal Landsat 8 Images for Crop Type Mapping in Southeastern Brazil , 2015, Remote. Sens..

[20]  R. Forman,et al.  ROADS AND THEIR MAJOR ECOLOGICAL EFFECTS , 1998 .

[21]  A. J. Richardsons,et al.  DISTINGUISHING VEGETATION FROM SOIL BACKGROUND INFORMATION , 1977 .

[22]  Douglas A. Stow,et al.  Land cover and land use change analysis using multi-spatial resolution data and object-based image analysis , 2018, Remote Sensing of Environment.

[23]  Jiaguo Qi,et al.  Differentiating anthropogenic modification and precipitation-driven change on vegetation productivity on the Mongolian Plateau , 2015, Landscape Ecology.

[24]  D. Goetze,et al.  Identification of driving factors of land degradation and deforestation in the Wildlife Reserve of Bontioli (Burkina Faso, West Africa) , 2015 .

[25]  Shenggong Li,et al.  Natural recovery of steppe vegetation on vehicle tracks in central Mongolia , 2006, Journal of Biosciences.

[26]  Aggelos K. Katsaggelos,et al.  A survey of classical methods and new trends in pansharpening of multispectral images , 2011, EURASIP J. Adv. Signal Process..

[27]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[28]  C. Tucker Red and photographic infrared linear combinations for monitoring vegetation , 1979 .

[29]  Qihao Weng,et al.  A survey of image classification methods and techniques for improving classification performance , 2007 .

[30]  Xianfeng Jiao,et al.  Spectral-analysis-based extraction of land disturbances arising from oil and gas development in diverse landscapes , 2017 .

[31]  Larry D. Hostetler,et al.  The estimation of the gradient of a density function, with applications in pattern recognition , 1975, IEEE Trans. Inf. Theory.

[32]  Elisabeth Schoepfer,et al.  Monitoring of Oil Exploitation Infrastructure by Combining Unsupervised Pixel-Based Classification of Polarimetric SAR and Object-Based Image Analysis , 2014, Remote. Sens..

[33]  Nan Yang,et al.  A review of road extraction from remote sensing images , 2016 .

[34]  Jeffrey E. Herrick,et al.  Assessing Transportation Infrastructure Impacts on Rangelands: Test of a Standard Rangeland Assessment Protocol , 2010 .

[35]  Aly M. El-naggar Determination of optimum segmentation parameter values for extracting building from remote sensing images , 2018 .

[36]  A. Gitelson,et al.  Spectral reflectance changes associated with autumn senescence of Aesculus hippocastanum L. and Acer platanoides L. leaves. Spectral features and relation to chlorophyll estimation , 1994 .