Data Mining Practical Machine Learning Tools and Techniques

Quantification of global forest change has been lacking despite the recognized importance of forest ecosystem services. In this study, Earth observation satellite data were used to map global forest loss (2.3 million square kilometers) and gain (0.8 million square kilometers) from 2000 to 2012 at a spatial resolution of 30 meters. The tropics were the only climate domain to exhibit a trend, with forest loss increasing by 2101 square kilometers per year. Brazil's well-documented reduction in deforestation was offset by increasing forest loss in Indonesia, Malaysia, Paraguay, Bolivia, Zambia, Angola, and elsewhere. Intensive forestry practiced within subtropical forests resulted in the highest rates of forest change globally. Boreal forest loss due largely to fire and forestry was second to that in the tropics in absolute and proportional terms. These results depict a globally consistent and locally relevant record of forest change.

High-Resolution Global Maps of 21st-Century Forest Cover Change

Global Land Cover (GLC) information is fundamental for environmental change studies, land resource management, sustainable development, and many other societal benefits. Although GLC data exists at spatial resolutions of 300 m and 1000 m, a 30 m resolution mapping approach is now a feasible option for the next generation of GLC products. Since most significant human impacts on the land system can be captured at this scale, a number of researchers are focusing on such products. This paper reports the operational approach used in such a project, which aims to deliver reliable data products. Over 10,000 Landsat-like satellite images are required to cover the entire Earth at 30 m resolution. To derive a GLC map from such a large volume of data necessitates the development of effective, efficient, economic and operational approaches. Automated approaches usually provide higher efficiency and thus more economic solutions, yet existing automated classification has been deemed ineffective because of the low classification accuracy achievable (typically below 65%) at global scale at 30 m resolution. As a result, an approach based on the integration of pixel- and object-based methods with knowledge (POK-based) has been developed. To handle the classification process of 10 land cover types, a split-and-merge strategy was employed, i.e. firstly each class identified in a prioritized sequence and then results are merged together. For the identification of each class, a robust integration of pixel-and object-based classification was developed. To improve the quality of the classification results, a knowledge-based interactive verification procedure was developed with the support of web service technology. The performance of the POK-based approach was tested using eight selected areas with differing landscapes from five different continents. An overall classification accuracy of over 80% was achieved. This indicates that the developed POK-based approach is effective and feasible for operational GLC mapping at 30 m resolution.

Global land cover mapping at 30 m resolution: A POK-based operational approach

Dynamics of global forest area: Results from the FAO Global Forest Resources Assessment 2015

Accurate land cover information is required for science, monitoring, and reporting. Land cover changes naturally over time, as well as a result of anthropogenic activities. Monitoring and mapping of land cover and land cover change in a consistent and robust manner over large areas is made possible with Earth Observation (EO) data. Land cover products satisfying a range of science and policy information needs are currently produced periodically at different spatial and temporal scales. The increased availability of EO data—particularly from the Landsat archive (and soon to be augmented with Sentinel-2 data)—coupled with improved computing and storage capacity with novel image compositing approaches, have resulted in the availability of annual, large-area, gap-free, surface reflectance data products. In turn, these data products support the development of annual land cover products that can be both informed and constrained by change detection outputs. The inclusion of time series change in the land cover mapping process provides information on class stability and informs on logical class transitions (both temporally and categorically). In this review, we present the issues and opportunities associated with generating and validating time-series informed annual, large-area, land cover products, and identify methods suited to incorporating time series information and other novel inputs for land cover characterization.

Optical remotely sensed time series data for land cover classification: A review

We have produced the first 30 m resolution global land-cover maps using Landsat Thematic Mapper TM and Enhanced Thematic Mapper Plus ETM+ data. We have classified over 6600 scenes of Landsat TM data after 2006, and over 2300 scenes of Landsat TM and ETM+ data before 2006, all selected from the green season. These images cover most of the world's land surface except Antarctica and Greenland. Most of these images came from the United States Geological Survey in level L1T orthorectified. Four classifiers that were freely available were employed, including the conventional maximum likelihood classifier MLC, J4.8 decision tree classifier, Random Forest RF classifier and support vector machine SVM classifier. A total of 91,433 training samples were collected by traversing each scene and finding the most representative and homogeneous samples. A total of 38,664 test samples were collected at preset, fixed locations based on a globally systematic unaligned sampling strategy. Two software tools, Global Analyst and Global Mapper developed by extending the functionality of Google Earth, were used in developing the training and test sample databases by referencing the Moderate Resolution Imaging Spectroradiometer enhanced vegetation index MODIS EVI time series for 2010 and high resolution images from Google Earth. A unique land-cover classification system was developed that can be crosswalked to the existing United Nations Food and Agriculture Organization FAO land-cover classification system as well as the International Geosphere-Biosphere Programme IGBP system. Using the four classification algorithms, we obtained the initial set of global land-cover maps. The SVM produced the highest overall classification accuracy OCA of 64.9% assessed with our test samples, with RF 59.8%, J4.8 57.9%, and MLC 53.9% ranked from the second to the fourth. We also estimated the OCAs using a subset of our test samples 8629 each of which represented a homogeneous area greater than 500 m × 500 m. Using this subset, we found the OCA for the SVM to be 71.5%. As a consistent source for estimating the coverage of global land-cover types in the world, estimation from the test samples shows that only 6.90% of the world is planted for agricultural production. The total area of cropland is 11.51% if unplanted croplands are included. The forests, grasslands, and shrublands cover 28.35%, 13.37%, and 11.49% of the world, respectively. The impervious surface covers only 0.66% of the world. Inland waterbodies, barren lands, and snow and ice cover 3.56%, 16.51%, and 12.81% of the world, respectively.

https://www.tandfonline.com/doi/pdf/10.1080/01431161.2012.748992

Finer resolution observation and monitoring of global land cover: first mapping results with Landsat TM and ETM+ data

Impact cratering process is the major geologic activity on the surface of the Moon, and the spatial distribution and size-frequency distribution of lunar craters are indicative to the bombardment history of the Solar System. The substantial efforts on the development of automated crater detection algorithms (CDAs) have been carried out on the images from the remote sensing observations. Recently, CDAs via convolutional neural network (CNN) on digital elevation model (DEM) has been developed as it can combine the discrimination ability of CNN with the robust characteristic of the DEM data. However, most of the existing algorithms adopt a traditional two-stage detection pipeline including an edge segmentation and a template matching step. In this paper, we attempt to reduce the gap between the existing DEM-based CDAs and the advanced CNN methods for object detection, and propose a complete workflow including an end-to-end deep learning pipeline for lunar crater detection, in particular for craters smaller than 50 km in diameter. Based on the workflow, we benchmark nine representative CNN models involving three popular types of detection architectures. Moreover, we elaborate on the practical application of the proposed workflow, and provide an example method to demonstrate the performance advantage in terms of the precision (82.97%) and recall (79.39%). Furthermore, we develop a crater verification tool to manually validate the detection results, and the visualization results show that our detected craters are reasonable and can be used as a supplement to the existing hand-labeled datasets.

/pdf/lunar-crater-detection-on-digital-elevation-model-a-complete-24f55par.pdf

Lunar Crater Detection on Digital Elevation Model: A Complete Workflow Using Deep Learning and Its Application

A laboratory study of the phase ratio imagery method

Numerous linear grooves have long been recognized as covering the surface of Phobos, but the mechanisms of their formation are still unclear. One possible mechanism is related to the largest crater on Phobos, the Stickney crater, whose impact ejecta may slide, roll, bounce, and engrave groove-like features on Phobos. When the launch velocity is higher than the escape velocity, the impact ejecta can escape Phobos. A portion of these high-velocity ejecta are dragged by the gravitational force of Mars, fall back, and reimpact Phobos. In this research, we numerically test the hypothesis that the orbital ejecta of the Stickney crater that reimpact Phobos could be responsible for a particular subset of the observed grooves on Phobos. We adopt impact hydrocode iSALE-2D (impact-Simplified Arbitrary Lagrangian Eulerian, two-dimensional) to simulate the formation of the Stickney crater and track its impact ejecta, with a focus on orbital ejecta with launch velocities greater than the escape velocity of Phobos. The launch velocity distribution of the ejecta particles is then used to calculate their trajectories in space and determine their fates. For orbital ejecta reimpacting Phobos, we then apply the sliding boulder model to calculate the ejecta paths, which are compared with the observed groove distribution and length to search for causal relationships. Our ejecta trajectory calculations suggest that only ~1% of the orbital ejecta from the Stickney crater can reimpact Phobos. Applying the sliding boulder model, we predict ejecta sliding paths of 9−20 km in a westward direction to the east of the zone of avoidance, closely matching the observed grooves in that region. The best-fit model assumes an ejecta radius of ~150 m and a speed restitution coefficient of 0.3, consistent with the expected ejecta and regolith properties. Our calculations thus suggest the groove class located to the east of the zone of avoidance may have been caused by reimpact orbital ejecta from the Stickney crater. 

Menghua Zhu

Papers

Finer resolution observation and monitoring of global land cover: first mapping results with Landsat TM and ETM+ data

Lunar Crater Detection on Digital Elevation Model: A Complete Workflow Using Deep Learning and Its Application

A laboratory study of the phase ratio imagery method

Groove formation on Phobos from reimpacting orbital ejecta of the Stickney crater