Fanjinshan National Nature Reserve (FNNR) is a biodiversity hotspot in China that is part of a larger, multi-use landscape where farming, grazing, tourism, and other human activities occur. The steep terrain and persistent cloud cover pose challenges to robust vegetation and land use mapping. Our objective is to develop satellite image classification techniques that can reliably map forest cover and land use while minimizing the cloud and terrain issues, and provide the basis for long-term monitoring. Multi-seasonal Landsat image composites and elevation ancillary layers effectively minimize the persistent cloud cover and terrain issues. Spectral vegetation index (SVI) products and shade/illumination normalization approaches yield significantly higher mapping accuracies, compared to non-normalized spectral bands. Advanced machine learning image classification routines are implemented through the cloud-based Google Earth Engine platform. Optimal classifier parameters (e.g., number of trees and number of features for random forest classifiers) were achieved by using tuning techniques. Accuracy assessment results indicate consistent and effective overall classification (i.e., above 70% mapping accuracies) can be achieved using multi-temporal SVI composites with simple illumination normalization and elevation ancillary data, despite the fact limited training and reference data are available. This efficient and open-access image analysis workflow provides a reliable methodology to remotely monitor forest cover and land use in FNNR and other mountainous forested, cloud prevalent areas.

Remote sensing scientists are increasingly adopting machine learning classifiers for land cover and land use (LCLU) mapping, but model selection, a critical step of the machine learning classification, has usually been ignored in the past research. In this paper, step-by-step guidance (for classifier training, model selection, and map production) with supervised learning model selection is first provided. Then, model selection is exhaustively applied to different machine learning (e.g. Artificial Neural Network (ANN), Decision Tree (DT), Support Vector Machine (SVM), and Random Forest (RF)) classifiers to identify optimal polynomial degree of input features (d) and hyperparameters with Landsat imagery of a study region in China and Ghana. We evaluated the map accuracy and computing time associated with different versions of machine learning classification software (i.e. ArcMap, ENVI, TerrSet, and R). The optimal classifiers and their associated polynomial degree of input features and hyperparameters vary for the two image datasets that were tested. The optimum combination of d and hyperparameters for each type of classifier was used across software packages, but some classifiers (i.e. ENVI and TerrSet ANN) were customized due to the constraints of software packages. The LCLU map derived from ENVI SVM has the highest overall accuracy (72.6%) for the Ghana dataset, while the LCLU map derived from R DT has the highest overall accuracy (48.0%) for the FNNR dataset. All LCLU maps for the Ghana dataset are more accurate compared to those from the China dataset, likely due to more limited and uncertain training data for the China (FNNR) dataset. For the Ghana dataset, LCLU maps derived from tree-based classifiers (ArcMap RF, TerrSet DT, and R RF) routines are accurate, but these maps have artefacts resulting from model overfitting problems.

Many studies have reported that the Arctic is greening; however, we lack an understanding of the detailed patterns and processes that are leading to this observed greening. The normalized difference vegetation index (NDVI) is used to quantify greening, which has had largely positive trends over the last few decades using low spatial resolution satellite imagery such as AVHRR or MODIS over the pan-Arctic region. However, substantial fine scale spatial heterogeneity in the Arctic makes this large-scale investigation hard to interpret in terms of vegetation and other environmental changes. Here we focus on one area of the northern Alaskan Arctic using high spatial resolution (4 m) multispectral satellite imagery from DigitalGlobe^™ to analyze the greening trend near Utqiaġvik (formerly known as Barrow) over 14 years from 2002 to 2016. We found that tundra vegetation has been greening (τ = 0.65, p = 0.01, NDVI increase of 0.01 yr⁻¹) despite no overall change in vegetation community composition. The greening is most closely correlated to the number of thawing degree days (R ² = 0.77, F = 21.5, p < 0.001) which increased in a similar linear trend over the 14 year study period (1.79 ± 0.50 days per year, p < 0.01, τ = −0.56). This suggests that in this Arctic ecosystem, greening is occurring due to a lengthening growing season that appears to stimulate plant productivity without any significant change in vegetation communities. We found that vegetation communities in wetter locations greened about twice as fast as those found in drier conditions supporting the hypothesis that these communities respond more strongly to warming. We suggest that in Arctic environments, vegetation productivity may continue to rise, particularly in wet areas.

The primary objective of this study was to compare the sensitivity of two different normalized difference vegetation index (NDVI) time series derived from Local Area Coverage (LAC) and Global Areal Coverage (GAC) data sets of the National Oceanic and Atmospheric Administration (NOAA) Advanced Very High Resolution Radiometer (AVHRR) satellite system. This comparison was conducted in the context of analysing spatiotemporal patterns of Arctic tundra vegetation greenness change in the 1990s within the North Slope of Alaska. A second objective was to examine patterns of greenness change with respect to the distribution of vegetation association types. An 8 km spatial resolution NDVI series was produced by the Global Inventory Modeling and Mapping Studies (GIMMS) group at the National Aeronautics and Space Administration (NASA) Goddard Space Flight Center based on a GAC data set and corrected for stratospheric aerosol effects from the eruption of Mt Pinatubo. The LAC (1 km spatial resolution) NDVI time series was generated through recalibration and fine‐tuning of image registration of a twice‐monthly time series produced by the US Geological Survey, and was cross‐calibrated with the GIMMS data set to reduce stratospheric aerosol effects from the Mt Pinatubo eruption. While the general patterns of pixels exhibiting significant increase in seasonally integrated NDVI over the 1990s were similar from both data sets, many of the more localized areas of more rapidly increasing greenness (i.e. ‘hotspots’) between 1990 and 1999 were lost with the product from the GIMMS data set. The majority of the ‘hotspots’ of greenness increase within the North Slope region are located in the southern portions of the foothills physiographic province and within vegetation units composed primarily of prostrate or dwarf shrubs with a mixture of graminoid species. Notably fewer hotspots of greenness increase were detected in Arctic tundra areas of the Seward Peninsula and none in the Chukotka Peninsula of the Russian Far East, an area that had not experienced the same warming trend in the 1990s and preceding decades as the Alaskan Arctic.

A segmentation and hierarchical classification approach applied to QuickBird multispectral satellite data was implemented, with the goal of delineating residential land use polygons and identifying low and high socio‐economic status of neighbourhoods within Accra, Ghana. Two types of object‐based classification strategies were tested, one based on spatial frequency characteristics of multispectral data, and the other based on proportions of Vegetation–Impervious–Soil sub‐objects. Both approaches yielded residential land‐use maps with similar overall percentage accuracy (75%) and kappa index of agreement (0.62) values, based on test objects from visual interpretation of QuickBird panchromatic imagery.

Time series of normalized difference indices (NDIs) derived from MODIS surface reflectance data provide potentially useful information for monitoring fuel moisture content (FMC) for fire risk assessment. The visible atmospherically resistant index (VARI) and normalized difference water index (NDWI) were compared for monitoring live FMC of chaparral shrublands. Regression coefficients are encouraging given disparate spatial resolutions of ground‐based FMC measurements and MODIS‐derived NDIs. VARI exhibited greater temporal co‐variability (0.79>r ²<0.94) and spatial robustness with FMC than NDWI, even though the former is based solely on visible waveband reflectance data.