Identifying woody vegetation on coal surface mines using phenological indicators with multitemporal Landsat imagery

Abstract

Commission VI, WG VI/4KEY WORDS: Afforestation, Ecosystem Recovery, Elaeagnus umbellata, Landsat, Land Cover Change, Mine Reclamation, Exotic Plants ABSTRACT:Surface mining for coal has disturbed large land areas in the Appalachian Mountains. Better information on mined lands' ecosystem recovery status is necessary for effective environmental management in mining-impacted regions. Because record quality varies between state mining agencies and much mining occurred prior to widespread use of geospatial technologies, accurate maps of mining extents, durations, and land cover effects are often not available. Landsat data are well suited to mapping and characterizing land cover and forest recovery on former coal surface mines. Past mine reclamation techniques have often failed to restore premining forest vegetation but natural processes may enable native forests to re-establish on mined areas with time. However, the invasive species autumn olive (Elaeagnus umbellate) is proliferating widely on former coal surface mines, often inhibiting reestablishment of native forests. Autumn olive outcompetes native vegetation because it fixes atmospheric nitrogen and benefits from a longer growing season than native deciduous trees. This longer growing season, along with Landsat 8's high signal to noise ratio, has enabled species-level classification of autumn olive using multitemporal Landsat 8 data at accuracy levels usually only obtainable using higher spatial or spectral resolution sensors. We have used classification and regression tree (CART ® ) and support vector machine (SVM) to classify five counties in the coal mining region of Virginia for presence and absence of autumn olive. The best model found was a CART ® model with 36 nodes which had an overall accuracy of 84% and kappa of 0.68. Autumn olive had conditional kappa of 0.65 and a producers and users accuracy of 86% and 83% respectively. The best SVM model used a second order polynomial kernel and had an overall accuracy of 77%, an overall kappa of 0.54 and a producers and users accuracy of 60% and 90% respectively.

Agricultural cropland extent and areas of South Asia derived using Landsat satellite 30-m time-series big-data using random forest machine learning algorithms on the Google Earth Engine cloud

“…The classification of South Asia requires large reference data because of variability in spectral signatures of varied land use/ land cover (LULC) within this large geographical area. In this regard, RF classification for each of the five AEZ produced far better results than classifying the whole area, an iterative approach was used to add and remove training samples, based on classification results, to improve the map classification and each map was visually assessed to see how well the classified map correlated with observed cropland in the landscape as seen in the sub-meter to 5-m VHRI (Oliphant et al 2014) primarily using WorldView-3 data. The RF MLA was mainly used to generate cropland and non-cropland classes in five AEZs.…”

Spatiotemporal Variability of Human Disturbance Impacts on Ecosystem Services in Mining Areas

“…However, mining sites also have substantial ecological, geological, and cultural value [23,[30][31][32][33][34]. On the other hand, the specific restoration method (e.g., Surface Mining Control and Reclamation Act of 1977 [35] and fast colonizing species [36]) alleviates soil destabilization and water-quality impairment to cause herbaceous communities to proliferate rapidly and widely in mines, while resulting in a poor growing environment for native trees that greatly hinder forest regeneration [37]. However, these studies focused on snapshots that provided limited information on ESs, and dynamic changes in ESs have seldom been examined [38].…”