Evaluating the performance of a new classifier – the GP-OAD: A comparison with existing methods for classifying rock type and mineralogy from hyperspectral imagery

In this study, we compare three commonly used methods for hyperspectral image classification, namely Support Vector Machines (SVMs), Gaussian Processes (GPs) and the Spectral Angle Mapper (SAM). We assess their performance in combination with different kernels (i.e. which use distance-based and angle-based metrics). The assessment is done in two experiments, under ideal conditions in the laboratory and, separately, in the field (an operational open pit mine) using natural light. For both experiments independent training and test sets are used. Results show that GPs generally outperform the SVMs, irrespective of the kernel used. Furthermore, angle-based methods, including the Spectral Angle Mapper, outperform GPs and SVMs when using distance-based (i.e. stationary) kernels in the field experiment. A new GP method using an angle-based (i.e. a non-stationary) kernel – the Observation Angle Dependent (OAD) covariance function – outperforms SAM and SVMs in both experiments using only a small number of training spectra. These findings show that distance-based kernels are more affected by changes in illumination between the training and test set than are angular-based methods/kernels. Taken together, this study shows that independent training data can be used for classification of hyperspectral data in the field such as in open pit mines, by using Bayesian machine-learning methods and non-stationary kernels such as GPs and the OAD kernel. This provides a necessary component for automated classifications, such as autonomous mining where many images have to be classified without user interaction.     

Monitoring intra and inter annual dynamics of forest degradation from charcoal production in Southern Africa with Sentinel – 2 imagery

The contribution of forest degradation to changes in forest carbon stocks remains poorly quantified and constitutes a main source of uncertainty in the forest carbon budget. Charcoal production is a major source of forest degradation in sub-Saharan Africa. We used multitemporal Sentinel-2 imagery to monitor and quantify forest degradation extent in the main supplying area of a major urban center of southern Africa over a 4-year period. We implemented an indirect approach combining Sentinel-2 imagery to map kiln and field measurements to estimate AGB removals and carbon losses from charcoal production. This work generated 10 m resolution maps of forest degradation extent from charcoal production in the study area at quarterly intervals from 2016–2019. These maps reveal an intense and rapid forest degradation process and expose the spatial and temporal patterns of forest degradation from charcoal production with high detail. The total area under charcoal production over the study period reached 26,647 ha (SD = 320.8) and the forest degradation front advanced 10.5 km in a 4-year period, with an average of 19.4 ha of woodlands degraded daily. By the end of 2019, charcoal production disturbed most mopane stands in the study area and woodland fragmentation increased in 70.4 % of the mopane woodlands. We estimated that charcoal production was responsible for 2,568,761 Mg (SD = 42,130) of aboveground biomass extracted from the forest and 1,284,381 Mg (SD = 21,075) of carbon loss. The magnitude of these figures underlines the relevance of charcoal production as a main cause of forest cover change and remarks the existing uncertainties in the quantification of forest degradation processes. These results illustrate the potential of multitemporal medium resolution imagery to quantify forest degradation in sub-Saharan Africa and improve REDD + Monitoring, Reporting, and Verification systems in compliance with international reporting commitments.     

Analyzing the impact of thermal stress on vegetation health and agricultural drought – a case study from Gujarat,India

Although poor precipitation due to delayed arrival and/or early retreat of the southwest monsoon is considered the chief architect of drought in India, heat waves may also play a crucial role in the intensification of droughts. In the Indian subcontinent, occurrence of heat waves during the pre-monsoon and high air-temperature in the subsequent monsoon season imparts thermal stress on vegetation causing degradation of vegetation health (VH). In the present study, various vegetation indices and land-use/land-cover data derived from multi-sensor satellite have been used to assess VH and agricultural drought in Gujarat during 1981–2010. This Geographical Information Systems-based study has also used heat wave and temperature data to analyze the adverse effects of high temperature on VH. The time series of Vegetation Condition Index and Temperature Condition Index (TCI) has shown that the combined influence of moisture-stress and thermal stress determines the occurrence and severity of drought, which is reflected in the Vegetation Health Index (VHI). A strong correlation among aboveground air-temperature, the TCI and the VHI indicates definite influence of thermal stress on VH. Further, a systematic variation and strong resemblance between temperature, crop yield, TCI and VHI has established the impact of thermal stress on agricultural productivity.     

Estimating the starting time and identifying the type of urbanization based on dense time series of landsat-derived Vegetation-Impervious-Soil (V-I-S) maps – A case study of North Taiwan from 1990 to 2015

Land cover and land use change (LCLUC) is a global phenomenon, and LCLUC in urbanizing regions has substantial impacts on humans and their environments. In this paper, a semi-automatic approach to identifying the type and starting time of urbanization was developed and tested based on dense time series of Vegetation-Impervious-Soil (V-I-S) maps derived from Landsat surface reflectance imagery. The accuracy of modeled V-I-S fractions and the estimated time of initial change in impervious cover were assessed. North Taiwan, one of the regions of the island of Taiwan that experienced the greatest urban LCLUC, was chosen as a test area, and the study period is 1990 to 2015, a period of substantial urbanization. In total, 295 dates of Landsat imagery were used to create 295 V-I-S fraction maps that were used to construct fractional cover time series for each pixel. Root Mean Square Error (RMSE)s for the modeled Vegetation, Impervious, and Soil were 25 %, 22 %, 24 % respectively. The time of Urban Expansion is estimated by logistic regression applied to Impervious cover time series, while the time of change for Urban Renewal is determined by the period of brief Soil exposure. The identified location and estimated time for newly urbanized lands were generally accurate, with 80% of Urban Expansion estimated within ±2.4 years. However, the accuracy of identified Urban Renewal was relatively low. Our approach to identifying Urban Expansion with dense time series of Landsat imagery is shown to be reliable, while Urban Renewal identification is not.     

Horizontal and vertical accuracy of Google Earth®: comment on ‘Positional accuracy of the Google Earth terrain model derived from stratigraphic unconformities in the Big Bend region,Texas, USA’ by S.C. Benker,R.P. Langford and T.L. Pavlis

Comment on ‘Positional accuracy of the Google Earth terrain model derived from stratigraphic unconformities in the Big Bend region, Texas, USA’ by S.C. Benker, R.P. Langford and T.L. Pavlis (Geocarto Int. 26:291–303, doi: 10.1080/10106049.2011.568125).