Browsing by Author "Khandelwal, Ankush"

Now showing 1 - 9 of 9
  • Thumbnail Image
    Item
    An approach for global monitoring of surface water extent variations using MODIS data
    (2016-08-29) Khandelwal, Ankush; Karpatne, Anuj; Marlier, Miriam E.; Kim, Jongyoun; Lettenmaier, Dennis P.; Kumar, Vipin
    Freshwater resources are among the most basic requirements of human society.  Nonetheless, global information about the space-time variations of the area of freshwater bodies, and the water stored in them, is surprisingly limited. We introduce a MODIS-based algorithm to map the global areal extent of surface water bodies at 500m spatial resolution at nominal eight-day intervals from 2000 to 2015. We demonstrate the algorithm construction and performance for five reservoirs on four continents with different shapes. The algorithm performs well compared to satellite radar altimetry and in situ height measurements, and in comparison with surface area estimates based on higher resolution Landsat data. We further present a summary of our global scale results over 69 reservoirs for which altimetry measurements are available, and show that our surface area estimates match well with relative height variations and show significant improvements over previous estimates. One of the main reasons for these improvements is a novel post-processing technique that makes use of imperfect labels produced by supervised classification approaches on multiple dates to estimate the elevation structure of locations that is used to enhance the quality and completeness of imperfect labels. However, the approach is still challenged in regions with frequent cloud cover, snow and ice coverage, or complicated geometries that require finer spatial resolution remote sensing data. The surface area estimates we describe here are publically available.
  • Thumbnail Image
    Item
    Automated Plantation Mapping in Southeast Asia Using Remote Sensing Data
    (2016-08-16) Jia, Xiaowei; Khandelwal, Ankush; Gerber, James; Carlson, Kimberly; West, Paul; Samberg, Leah; Kumar, Vipin
    Plantation mapping is critical for understanding and addressing deforestation, a key driver of climate change and ecosystem degradation. Unfortunately, most plantation maps are limited to small areas for specific years because they rely on visual inspection of imagery. Here we propose an automated approach for annual mapping of plantations using remote sensing data. Due to the heterogeneity of land cover classes, we propose a novel ensemble learning method that simultaneously uses training samples from multiple land cover classes over different years. After the ensemble learning, we further improve the performance by post-processing using a Hidden Markov Model. With the experiments on MODIS data, we demonstrate the superiority of the proposed method over multiple baselines. In addition, we conduct extensive validation by comparing the detected plantation by our approach with the existing datasets developed through visual interpretation by expert observers. Based on the random sampling and the comparison with high-resolution images, the precision (i.e. user’s accuracy) and recall (i.e. producer’s accuracy) of our generated map are around 85.53% and 81.51%, respectively, and the overall accuracy is 95.20%.
  • Thumbnail Image
    Item
    GLADD-R: A new Global Lake Dynamics Database for Reservoirs created using machine learning and satellite data
    (2019-04-01) Khandelwal, Ankush; Karpatne, Anuj; Wei, Zhihao; Kuang, Huangying; Ghosh, Rahul; Dugan, Hilary; Hanson, Paul; Kumar, Vipin
    Reservoirs play a crucial role for human sustenance as they provide freshwater for agriculture, power generation, human consumption, and recreation. A global database of reservoirs that provides their location and dynamics can be of great importance to the ecological community as it enables the study of the impact of human actions and climate change on fresh water availability. Here we present a new database, GLADD-R (Global Lake Dynamics Database-Reservoirs) that provides such information for 1882 reservoirs between 1 and 100 square kilometers in size that were created after 1985. The visualization of these reservoirs and their surface area time series is available at http://umnlcc.cs.umn.edu/GlobalReservoirDatabase/.
  • Thumbnail Image
    Item
    Global Lake Monitoring using Group-specific Local Learning
    (2014-10-09) Karpatne, Anuj; Khandelwal, Ankush; Kumar, Vipin
    Global lake monitoring is crucial for the effective management of water resources as well as for conducting studies that link the impact of lake dynamics on climate change. Remote sensing datasets offer an opportunity for global lake monitoring by providing discriminatory features that can help distinguish land and water bodies at a global scale and in a timely fashion. A major challenge in global lake monitoring using remote sensing datasets is the presence of a rich variety in the land and water bodies at a global scale, motivating the need for local learning algorithms that can take into account the heterogeneity in the data. We propose a novel group-specific local learning scheme that uses information about the local neighborhood of a group of test instances for estimating the relevant context for classification. By comparing the performance of the proposed scheme with baseline approaches over 180 lakes from diverse regions of the world, we are able to demonstrate that the proposed scheme provides significant improvements in the classification performance.
  • Thumbnail Image
    Item
    Mapping Burned Areas in Tropical forests using MODIS data
    (2016-09-02) Mithal, Varun; Nayak, Guruprasad; Khandelwal, Ankush; Kumar, Vipin; Nemani, Ramakrishna; Oza, Nikunj C.
    This paper presents a new burned area product for the tropical forests in South America and South-east Asia. The product is derived from Moderate Resolution Imaging Spectroradiometer (MODIS) multispectral surface reflectance data and Active Fire hotspots using a novel rare class detection framework that builds data-adaptive classification models for different spatial regions and land cover classes. Burned areas are reported for 9 MODIS tiles at a spatial resolution of 500 m in the study period from 2001 to 2014. The total burned area detected in the tropical forests of South America and South-east Asia during these years is 2,286,385 MODIS pixels (approximately 571 K sq. km.), which is more than three times compared to the estimates by the state-of-the art MODIS MCD64A1 (742,886 MODIS pixels). We also present validation of this burned area product using (i) manual inspection of Landsat false color composites before and after burn date, (ii) manual inspection of synchronized changes in vegetation index time series around the burn date, and (iii) comprehensive quantitative validation using MODIS-derived differenced Normalized Burn Ratio (dNBR). Our validation results indicate that the events reported in our product are indeed true burn events that are missed by the state-of-art burned area products.
  • Thumbnail Image
    Item
    ORBIT (Ordering Based Information Transfer): A Physics Guided Machine Learning Framework to Monitor the Dynamics of Water Bodies at a Global Scale
    (2019-05) Khandelwal, Ankush
    Predictive learning approaches along with vast amounts Earth Observation data offer a great opportunity to track changes on the earth's surface. However, due to data quality issues (sensor anomalies and atmospheric disturbances) and heterogeneity in the land surface, even state of the art machine learning algorithms perform poorly when applied on a global scale. Furthermore, due to inherent trade-off in sensor design, a single source does not provide both high spatial and temporal resolution required by various scientific applications. This thesis focuses on developing new machine learning algorithms that can leverage physical principles governing geo-physical processes to overcome these challenges, in the context of monitoring surface water changes at global scale. The thesis introduces a new framework, ORBIT (Ordering Based Information Transfer) that uses an implicit ordering constraint among instances to address the aforementioned challenges. For this application, the topography (the elevation structure) enforces such an ordering. This elevation constraint, however, is not available explicitly in almost all the cases. This thesis introduces a new rank aggregation approach to infer the inherent ordering from the noisy labels. This thesis also introduces a new approach that makes use of this elevation constraint to enforce temporal consistency in surface area variations of water bodies. Finally, this thesis introduces a new approach to downscale low resolution land/water masks to a higher spatial resolution using elevation ordering available at high resolution.
  • Thumbnail Image
    Item
    ReaLSAT: A new Reservoir and Lake Surface Area Timeseries Dataset created using machine learning and satellite imagery
    (2020-08-04) Khandelwal, Ankush; Ghosh, Rahul; Wei, Zhihao; Kuang, Huangying; Dugan, Hilary; Hanson, Paul; Karpatne, Anuj; Kumar, Vipin
    Lakes and reservoirs, as most humans experience and use them, are dynamic three-dimensional bodies of water, with surface levels that rise and fall with seasonal precipitation patterns, long-term changes in climate, and human management decisions. A global dataset that provides the location and dynamics of water bodies can be of great importance to the ecological community as it enables the study of the impact of human actions and climate change on fresh water availability. This paper presents a new database, ReaLSAT (Reservoir and Lake Surface Area Timeseries) that has been created by analyzing spectral data from Earth Observation (EO) Satellites using novel machine learning (ML) techniques. These ML techniques can construct highly accurate surface area extents of water bodies at regular intervals despite the challenges arising from heterogeneity and missing or poor quality spectral data. The ReaLSAT dataset provides information for 669107 lakes and reservoirs between 0.1 and 100 square kilometers in size. The visualization of these water bodies and their surface area time series is also available online. The aim of this paper is to provide an overview of the dataset and a summary of some of the key insights that can be derived from the dataset.
  • Thumbnail Image
    Item
    Source Aware Modulation for leveraging limited data from heterogeneous sources
    (2021) Li, Xiang; Khandelwal, Ankush; Ghosh, Rahul; Renganathan, Arvind; Willard, Jared; Xu, Shaoming; Jia, Xiaowei; Shu, Lele; Teng, Victor; Steinbach, Michael; Nieber, John; Duffy, Christopher; Kumar, Vipin
    In many personalized prediction applications, sharing information between entities/tasks/sources is critical to address data scarcity. Furthermore, inherent characteristics of sources distinguish relationships between input drivers and response variables across entities. For example, for the same amount of rainfall (input driver), two different basins will have very different streamflow (response variable) values depending on the basin characteristics (e.g., soil porosity, slope, …). Given such heterogeneity, a trivial merging of data without source characteristics would lead to poor personalized predictions. In recent years, meta-learning has become a very popular framework to learn generalized global models that can be easily adapted (fine-tuned) for individual sources. In this talk, we present an exhaustive analysis of the source-aware modulation based meta-learning approach. Source-aware modulation adjusts the shared hidden features based on source characteristics. The adjusted hidden features are then used to calculate the response variable for individual sources. Although this strategy shows promising prediction improvement, its applicability is limited in certain applications where source characteristics might not be available (especially due to privacy concerns). In this work, we show that robust personalized predictions can be achieved even in the absence of explicit source characteristics. We investigated the performance of different modulation strategies under various data sparsity settings on two datasets. We demonstrate that source-aware modulation is a very viable solution (with or without known characteristics) compared to traditional meta-learning methods such as model agnostic meta-learning.
  • Thumbnail Image
    Item
    Supplement for "Change Detection from Temporal Sequences of Class Labels: Application to Land Cover Change Mapping"
    (2013-01-25) Mithal, Varun; Khandelwal, Ankush; Boriah, Shyam; Steinhaeuser, Karsten; Kumar, Vipin
    This is a supplement for paper titled "Change Detection from Temporal Sequences of Class Labels: Application to Land Cover Change Mapping" which is included in proceedings of SIAM International Conference of Data Mining, 2013. This supplement section has enlarged figures mentioned in the main paper and additional experiments on synthetic data.