Prajjwal Panday

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.

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.

HIMALA: climate impacts on glaciers, snow, and hydrology in the Himalayan region

Abstract Glaciers are the largest reservoir of freshwater on Earth, supporting one third of the worlds population. The Himalaya possess one of the largest resources of snow and ice, which act as a freshwater reservoir for more than 1.3 billion people. This article describes a new project called HIMALA, which focuses on utilizing satellite-based products for better understanding of hydrological processes of the river basins of the region. With support from the US Agency for International Development (USAID), the International Centre for Integrated Mountain Development (ICIMOD), together with its partners and member countries, has been working on the application of satellite-based rainfall estimates for flood prediction. The US National Aeronautics and Space Administration (NASA) partners are working with ICIMOD to incorporate snowmelt and glacier melt into a widely used hydrological model. Thus, through improved modeling of the contribution of snow and ice meltwater to river flow in the region, the HIMALA project will improve the ability of ICIMOD and its partners to understand the impact of weather and climate on floods, droughts, and other water- and climate-induced natural hazards in the Himalayan region in Afghanistan, Bangladesh, Bhutan, China, India, Myanmar, Nepal, and Pakistan.

The Hydrology and Energy Balance of the Amazon Basin

The Amazon basin is the planet’s largest and most intense land-based centre of precipitation. This convective system is driven by high net surface radiation, which is dissipated via fluxes of latent heat and sensible heat. Over the long term (1 year or greater), incoming precipitation over the basin is balanced by evaporative fluxes of water to the atmosphere and discharge, which returns excess water to the oceans. The temporal variability of this cycle is largely controlled by oscillations of tropical Pacific and North Atlantic sea surface temperatures, while synergies between climate and forest structure and functioning control much of the observed spatial variability. Field observations and numerical models indicate that large-scale deforestation has decreased net surface radiation and evapotranspiration, increasing sensible heat flux, water yield, and stream discharge in many locations, particularly in the agricultural frontier of southeastern Amazonia. In the future, increasing atmospheric greenhouse gases are expected to increase temperatures, drought frequency, and drought intensity in the Amazon, causing further changes to the cycling of energy and water in the basin.