Bardan Ghimire

Contextual land-cover classification: incorporating spatial dependence in land-cover classification models using random forests and the Getis statistic

Land-cover characterization of large heterogeneous landscapes is challenging because of the confusion caused by high intra-class variability and heterogeneous landscape artefacts. Neighbourhood context can be used to supplement spectral information, and a novel way of incorporating spatial dependence in a heterogeneous region is tested here using an ensemble learning technique called random forests and a measure of local spatial dependence called the Getis statistic. The overall Kappa accuracy of the random forest classifier that used a combination of spectral and local spatial (Getis) variables at three different neighbourhood sizes (3 × 3, 7 × 7, and 11 × 11) ranged from 0.85 to 0.92. This accuracy was higher than that of a non-spatial random forest classifier having an overall Kappa accuracy of 0.78, which was run using the spectral variables only. This study demonstrated that the use of the Getis statistic with different neighbourhood sizes leads to substantial increase in per class classification accuracy of heterogeneous land-cover categories.

Seasonal trend analysis of image time series

A procedure is introduced for the analysis of seasonal trends in time series of Earth observation imagery. Called Seasonal Trend Analysis (STA), the procedure is based on an initial stage of harmonic analysis of each year in the series to extract the annual and semi‐annual harmonics. Trends in the parameters of these harmonics over years are then analysed using a robust median‐slope procedure. Finally, images of these trends are used to create colour composites highlighting the amplitudes and phases of seasonality trends. The technique specifically rejects high‐frequency sub‐annual noise and is robust to short‐term interannual variability up to a period of 29% of the length of the series. It is, thus, a very effective procedure for focusing on the general nature of longer‐term trends in seasonality.

An evaluation of bagging, boosting, and random forests for land-cover classification in Cape Cod, Massachusetts, USA

The iterative and convergent nature of ensemble learning algorithms provides potential for improving classification of complex landscapes. This study performs land-cover classification in a heterogeneous Massachusetts landscape by comparing three ensemble learning techniques (bagging, boosting, and random forests) and a non-ensemble learning algorithm (classification trees) using multiple criteria related to algorithm and training data characteristics. The ensemble learning algorithms had comparably high accuracy (Kappa range: 0.76-0.78), which was 11% higher than that of classification trees. Ensemble learning techniques were not influenced by calibration data variability, were robust to one-fifth calibration data noise, and insensitive to a 50% reduction in calibration data size.

Mapping seasonal trends in vegetation using AVHRR-NDVI time series in the Yucatán Peninsula, Mexico

This research examines the spatio-temporal trends in Advanced Very High Resolution Radiometer (AVHRR) Global Inventory Modelling and Mapping Studies (GIMMS) normalized difference vegetation index (NDVI) time series to ascribe land use change and precipitation to observed changes in land cover from 1982 to 2007 in the Mexican Yucatán Peninsula, using seasonal trend analysis (STA). In addition to discrete land cover transitions across the study region, patterns of agricultural intensification, urban expansion and afforestation in protected areas have enacted changes to the seasonal patterns of apparent greenness observed through STA greenness parameters. The results indicate that the seasonal variation in NDVI can be used to distinguish among different land cover transitions, and the primary differences among these transitions were in changes in overall greenness, peak annual greenness and the timing of the growing season. Associations between greenness trends and precipitation were weak, indicating a human-dominated system for the 26 years examined. Changes in the states of Campeche, Quintana Roo and Yucatán appear to be associated with pasture cultivation, urban expansion-extensive cultivation and urban expansion-intensive cultivation, respectively.

Global albedo change and radiative cooling from anthropogenic land cover change, 1700 to 2005 based on MODIS, land use harmonization, radiative kernels, and reanalysis

Widespread anthropogenic land cover change over the last five centuries has influenced the global climate system through both biogeochemical and biophysical processes. Models indicate that warming from carbon emissions associated with land cover conversion has been partially offset by cooling from elevated albedo, but considerable uncertainty remains partly because of uncertainty in model treatments of albedo. This study incorporates a new spatially and temporally explicit, land cover specific albedo product derived from Moderate Resolution Imaging Spectroradiometer with a historical land use data set (Land Use Harmonization product) to provide more precise, observationally derived estimates of albedo impacts from anthropogenic land cover change with a complete range of data set specific uncertainty. The mean annual global albedo increase due to land cover change during 1700–2005 was estimated as 0.00106 ± 0.00008 (mean ± standard deviation), mainly driven by snow exposure due to land cover transitions from natural vegetation to agriculture. This translates to a top-of-atmosphere radiative cooling of −0.15 ± 0.1 W m−2 (mean ± standard deviation). Our estimate was in the middle of the Intergovernmental Panel on Climate Change Fifth Assessment Report range of −0.05 to −0.25 W m−2 and incorporates variability in albedo within land cover classes.

Multiscale climatological albedo look-up maps derived from moderate resolution imaging spectroradiometer BRDF/albedo products

Abstract Surface albedo determines radiative forcing and is a key parameter for driving Earth’s climate. Better characterization of surface albedo for individual land cover types can reduce the uncertainty in estimating changes to Earth’s radiation balance due to land cover change. This paper presents albedo look-up maps (LUMs) using a multiscale hierarchical approach based on moderate resolution imaging spectroradiometer (MODIS) bidirectional reflectance distribution function (BRDF)/albedo products and Landsat imagery. Ten years (2001 to 2011) of MODIS BRDF/albedo products were used to generate global albedo climatology. Albedo LUMs of land cover classes defined by the International Geosphere-Biosphere Programme (IGBP) at multiple spatial resolutions were generated. The albedo LUMs included monthly statistics of white-sky (diffuse) and black-sky (direct) albedo for each IGBP class for visible, near-infrared, and shortwave broadband under both snow-free and snow-covered conditions. The albedo LUMs were assessed by using the annual MODIS IGBP land cover map and the projected land use scenarios from the Intergovernmental Panel on Climate Change land-use harmonization project. The comparisons between the reconstructed albedo and the MODIS albedo data product show good agreement. The LUMs provide high temporal and spatial resolution global albedo statistics without gaps for investigating albedo variations under different land cover scenarios and could be used for land surface modeling.

Time-series analysis of NDVI from AVHRR data over the Hindu Kush–Himalayan region for the period 1982–2006

The Hindu Kush–Himalayan (HKH) region with its surrounding mountains in central Asia is a region that has been warming at an alarming rate and is sensitive to climate change due to its heterogeneous terrain and high altitude. In a region where research is limited due to the paucity of field-based biophysical observations, analysis of remotely sensed data such as the normalized difference vegetation index (NDVI) can provide invaluable information on spatio-temporal patterns in linkages among land use, climate and vegetative phenological cycles, and trends in vegetative cover. In this study, NDVI data with 8 km spatial resolution for each 15 day composite period from 1982 to 2006 were analysed using a seasonal trend analysis technique, where the first step determines the annual mean and seasonal NDVI patterns across the HKH region. The second step analyses the non-parametric trends in magnitude and timing of the annual mean and seasonal NDVI cycle. The seasonal vegetation cycles were compared for the first and last ten years of the time series and were also analysed across areas undergoing significant change. Results indicated an overall greening trend in NDVI magnitude in most areas, particularly over open shrubland, grassland and cropland. Trends in the annual seasonal timing of NDVI indicated an earlier green-up for most parts of this region. Results also confirmed deforestation trends observed in a few states in northeastern India and Myanmar (Shan state) within the HKH region.