2835 research outputs found
Sort by
RSCDNet: A Robust Deep Learning Architecture for Change Detection From Bi-Temporal High Resolution Remote Sensing Images
Get PDFAccurate change detection from high-resolution satellite and aerial images is of great significance in remote sensing for precise comprehension of Land cover (LC) variations. The current methods compromise with the spatial context; hence, they fail to detect and delineate small change areas and are unable to capture the difference between features of the bi-temporal images. This paper proposes Remote Sensing Change Detection Network (RSCDNet) - a robust end-to-end deep learning architecture for pixel-wise change detection from bi-temporal high-resolution remote-sensing (HRRS) images. The proposed RSCDNet model is based on an encoder-decoder framework integrated with the Modified Self-Attention (MSA) andthe Gated Linear Atrous Spatial Pyramid Pooling (GL-ASPP) blocks; both efficient mechanisms to regulate the field-of-view while finding the most suitable trade-off between accurate localization and context assimilation. The paper documents the design and development of the proposed RSCDNet model and compares its qualitative and quantitative results with state-of-the-art HRRS change detection architectures. The above mentioned novelties in the proposed architecture resulted in an F1-score of 98%, 98%, 88%, and 75% on the four publicly available HRRS datasets namely, Staza-Tisadob, Onera, CD-LEVIR, and WHU. In addition to the improvement in the performance metrics, the strategic connections in the proposed GL-ASPP and MSA units significantly reduce the prediction time per image (PTPI) and provide robustness against perturbations. Experimental results yield that the proposed RSCDNet model outperforms the most recent change detection benchmark models on all four HRRS datasets
Rural-Urban Transition and Food Security in India (MiFood Paper No. 12)
Get PDFAs a growing proportion of world’s population lives in cities and towns, food security is increasingly acquiring an urban
character. The locus of food security research and policy agendas has correspondingly expanded from rural areas to include
cities and towns in the past few years. However, the dominant discourse on urbanization-food security relationship appears
to be shaped by perspectives from the Global North and large cities, and shows a lack of adequate understanding of the
urbanization-food security nexus in the small towns of the Global South. This paper aims to correct this bias. With a focus
on India where urban growth is increasingly concentrated in small, former rural regions, this paper reviews the food and
nutrition security implications of the country’s rural-urban transition. It identifies three conceptual pathways through which
to understand the bearing of rural-urban transition on food and nutrition security that include: livelihood change, land use
change, and dietary change. The evidence reviewed suggests the overall worsening of food and nutrition security for people
in this rural-urban transition, particularly for the poor populations. The paper also identifies several key research questions
and calls for more research on the urbanization-food security nexus in India
Landing the ‘Tiger of Rivers’: Understanding Recreational Angling of Mahseers in India using YouTube Videos
Get PDFMegafish mahseers popularly known as the ‘tiger of rivers’, are the dream catch of recreational anglers in India. The present study explored the Recreational Angling (RA) videos of five mahseer species Tor khudree (deccan mahseer), T. putitora (golden mahseer), T. remadevii (humpback mahseer), T. mosal (mosal mahseer) and Neolissochilus hexagonolepis (chocolate mahseer) recorded from India and uploaded on the social media platform YouTube from January 2010 to October 2022. We did not come across any RA videos of T. mosal and T. remadevii on YouTube hence further analyses were carried out on the remaining three focal species. No seasonality was observed in the frequency of RA videos uploaded on YouTube and T. khudree attracted the highest number of views per video. Catch and Release (C&R), an ethical RA practice was noticeably low in the case of N. hexagonolepis. The size of the catch was found to be positively associated with the social engagement received by the RA videos of all the three mahseer species focused. Angler and angling-related remarks and words associated with the emotion ‘trust’ dominated the comments received by the videos. The results are discussed in light of the trending discourses on developing social media data as a complementary tool for monitoring and managing RA and conserving fish
Seasonal Variability in Fine Particulate Matter Water Content and Estimated pH over a Coastal Region in the Northeast Arabian Sea
No full textThe acidity of atmospheric particles can promote specific chemical processes that result in the production of extra condensed phases from lesser volatile species (secondary fine particulate matter), change the optical and water absorption characteristics of particles, and enhance trace metal solubility that can function as essential nutrients in nutrient-limited environments. In this study, we present an estimated pH of fine particulate matter (FPM) through a thermodynamic model and assess its temporal variability over a coastal location in the northeast Arabian Sea. Here, we have used the chemical composition of FPM (PM2.5) collected during the period between 2017–2019. Chemical composition data showed large variability in water-soluble ionic concentrations (WSIC; range: 2.3–39.9 μg m−3) with higher and lower average values during the winter and summer months, respectively. SO42− ions were predominant among anions, while NH4+ was a major contributor among cations throughout the season. The estimated pH of FPM from the forward and reverse modes exhibits a moderate correlation for winter and summer samples. The estimated pH of FPM is largely regulated by SO42− content and strongly depends on the relative ambient humidity, particularly in the forward mode. Major sources of FPM assessed based on Positive matrix factorization (PMF) and air-mass back trajectory analyses demonstrate the dominance of natural sources (sea salt and dust) during summer months, anthropogenic sources in winter months and mixed sources during the post-monsoon seaso
Permutation Decision Trees
No full textDecision Tree is a well understood Machine Learning model that is based on minimizing impurities in the internal nodes. The most common impurity measures are Shannon entropy and Gini impurity. These impurity measures are insensitive to the order of training data and hence the final tree obtained is invariant to any permutation of the data. This leads to a serious limitation in modeling data instances that have order dependencies. In this work, we propose the use of Effort-To-Compress (ETC) - a complexity measure, for the first time, as an impurity measure. Unlike Shannon entropy and Gini impurity, structural impurity based on ETC is able to capture order dependencies in the data, thus obtaining potentially different decision trees for different permutations of the same data instances (Permutation Decision Trees). We then introduce the notion of Permutation Bagging achieved using permutation decision trees without the need for random feature selection and sub-sampling. We compare the performance of the proposed permutation bagged decision trees with Random Forests. Our model does not assume that the data instances are independent and identically distributed. Potential applications include scenarios where a temporal order present in the data instances is to be respected
Issue Brief III: India and China in the Arctic
Get PDFIndia and China, though non-Arctic states, have been active in the Arctic region. Both these countries were granted an ‘Observer’ status in the Arctic Council, a forum of all Arctic nations. India’s prime interest in Arctic is scientific as the changing climate can affect its monsoonal pattern and impact its food security. China’s main interest is strategic and economic development of Arctic as well as climate change and has clear policy on these aspects. India is in process of formulating its policy; it has already prepared a draft. Various aspects of India and China’s engagements in Arctic have been discussed. The development of the Arctic should be for a global good, while preserving its environment
Articulation work: Value chains of land assembly and real estate development on a peri-urban frontier
Get PDFIf the entanglements of real estate and finance capital are pivotal in ongoing urban transformations in cities of the global south, then a less visible but equally vital dimension is the process of land assembly on which residential and commercial real estate speculation and development are premised. This paper pries open the value chain of land assembly that underlies these transformations in a rapidly expanding peri-urban frontier of Bengaluru, India. Drawing on detailed interviews with land market intermediaries, operating across different scales, who were instrumental in assembling agricultural land for a large apartment complex, the paper shows how existing forms of social power and local knowledge are harnessed to create inter-scalar linkages that enable the creation and extraction of value in Indian real estate. It makes the case for understanding the economic and cultural work of intermediaries in animating land's value chain as ‘articulation work’. Finally, the paper assesses the varying forms and quantum of value that are generated and captured by different actors in the value chain, which stretches from the landowning farmer up to a major real estate company, to reflect on the micro-dynamics of speculative urbanism and agrarian urbanization
Caste and Capital
No full textThe chapter explores the historical and contemporary entanglements of caste and capital accumulation in India, drawing mainly on sociological literature