Terrestrial oil spill mapping using satellite earth observation and machine learning: A case study in South Sudan.

Terrestrial oil spills are a major threat to environmental and human well-being. Rapid, accurate, and remote spatial assessment of oil contamination is critical to implementing countermeasures that prevent potentially lasting ecological damage and irreversible harm to local communities. Satellite remote sensing has been used to support such assessments in inaccessible regions, although mapping small terrestrial oil spills is challenging - partly due to the pixel size of remote sensing systems, but also due to the distinguishability of small oil spill areas from other land cover types. We assessed the usability of freely available Sentinel satellite images to map terrestrial oil spills with machine learning algorithms. Using two test sites in South Sudan, we demonstrated that information from the Sentinel-1 and -2 instruments can be used to map oil spills with more than 90 % classification accuracy. Classification accuracy was significantly increased (>95 %) with the addition of multi-temporal information and spatial predictor variables that quantify proximity to oil production infrastructure such as pipelines and oil pads. The mapping of terrestrial oil spills with freely available Sentinel satellite images may thus represent an accurate and efficient means for the regular monitoring of oil-impacted areas.

Drought hazard in Kazakhstan in 2000-2016: a remote sensing perspective.

Droughts have significant negative impacts on livelihoods and economy of Kazakhstan. In this study, we assessed and characterized drought hazard events in Kazakhstan using satellite Remote Sensing time series for the period between 2000 and 2016. First, we calculated Vegetation Condition Index (VCI) and Standardized Enhanced Vegetation Index anomalies (ZEVI) based on 250 m Moderate Resolution Imaging Spectroradiometer (MODIS) Enhanced Vegetation Index (EVI) time series. Second, we assessed vegetation cover changes for the observation period. Third, we analyzed different characteristics of the drought hazard as well as spatial distribution of the drought-affected areas within the country. The results confirmed that drought was one of the environmental challenges for Kazakhstan in 2000-2016. The obtained maps showed that drought hazard conditions were observed every year, though the areal coverage of the drought conditions largely varied between the analyzed years. The calculated drought indices indicated that in years 2000, 2008, 2010, 2011, 2012, and 2014, more than 50% of the area of the country were affected by drought conditions of different severity with the largest droughts in terms of the areal spread occurring in 2012 and 2014. We concluded that the pre-requisite of successful implementation of drought hazard and risk mitigation strategies is availability of spatially explicit, timely, and reliable information on drought hazard. This suggests the necessity of incorporation of remote sensing-based drought information, as was demonstrated in this paper, in the national drought monitoring system of Kazakhstan.

National-scale cropland mapping based on spectral-temporal features and outdated land cover information.

The lack of sufficient ground truth data has always constrained supervised learning, thereby hindering the generation of up-to-date satellite-derived thematic maps. This is all the more true for those applications requiring frequent updates over large areas such as cropland mapping. Therefore, we present a method enabling the automated production of spatially consistent cropland maps at the national scale, based on spectral-temporal features and outdated land cover information. Following an unsupervised approach, this method extracts reliable calibration pixels based on their labels in the outdated map and their spectral signatures. To ensure spatial consistency and coherence in the map, we first propose to generate seamless input images by normalizing the time series and deriving spectral-temporal features that target salient cropland characteristics. Second, we reduce the spatial variability of the class signatures by stratifying the country and by classifying each stratum independently. Finally, we remove speckle with a weighted majority filter accounting for per-pixel classification confidence. Capitalizing on a wall-to-wall validation data set, the method was tested in South Africa using a 16-year old land cover map and multi-sensor Landsat time series. The overall accuracy of the resulting cropland map reached 92%. A spatially explicit validation revealed large variations across the country and suggests that intensive grain-growing areas were better characterized than smallholder farming systems. Informative features in the classification process vary from one stratum to another but features targeting the minimum of vegetation as well as short-wave infrared features were consistently important throughout the country. Overall, the approach showed potential for routinely delivering consistent cropland maps over large areas as required for operational crop monitoring.

Timely monitoring of Asian Migratory locust habitats in the Amudarya delta, Uzbekistan using time series of satellite remote sensing vegetation index.

The Asian Migratory locust (Locusta migratoria migratoria L.) is a pest that continuously threatens crops in the Amudarya River delta near the Aral Sea in Uzbekistan, Central Asia. Its development coincides with the growing period of its main food plant, a tall reed grass (Phragmites australis), which represents the predominant vegetation in the delta and which cover vast areas of the former Aral Sea, which is desiccating since the 1960s. Current locust survey methods and control practices would tremendously benefit from accurate and timely spatially explicit information on the potential locust habitat distribution. To that aim, satellite observation from the MODIS Terra/Aqua satellites and in-situ observations were combined to monitor potential locust habitats according to their corresponding risk of infestations along the growing season. A Random Forest (RF) algorithm was applied for classifying time series of MODIS enhanced vegetation index (EVI) from 2003 to 2014 at an 8-day interval. Based on an independent ground truth data set, classification accuracies of reeds posing a medium or high risk of locust infestation exceeded 89% on average. For the 12-year period covered in this study, an average of 7504 km2 (28% of the observed area) was flagged as potential locust habitat and 5% represents a permanent high risk of locust infestation. Results are instrumental for predicting potential locust outbreaks and developing well-targeted management plans. The method offers positive perspectives for locust management and treatment of infested sites because it is able to deliver risk maps in near real time, with an accuracy of 80% in April-May which coincides with both locust hatching and the first control surveys. Such maps could help in rapid decision-making regarding control interventions against the initial locust congregations, and thus the efficiency of survey teams and the chemical treatments could be increased, thus potentially reducing environmental pollution while avoiding areas where treatments are most likely to cause environmental degradation.