Search for: All records

A new framework for advanced machine learning-based analysis of hyperspectral datasets HSKL was built using the well-known package scikit-learn. In this paper, we describe HSKL’s structure and basic usage. We also showcase the diversity of models supported by the package by applying 17 classification algorithms and measure their baseline performance in segmenting objects with highly similar spectral properties. 

Advanced algorithms used in geospatial imaging were adopted for biomedical application to analyze hyperspectral datasets. To demonstrate the effectiveness, endmember extractions method was applied for delineating tumors in animal models of cancer. 

Multi- and hyperspectral imaging modalities encompass a growing number of spectral techniques that find many applications in geospatial, biomedical and machine vision fields. The rapidly increasing number of applications requires a convenient easy-to-navigate software that can be used by new and experienced users to analyze data, develop, apply, and deploy novel algorithms. Herein, we present our platform, IDCube that performs essential operations in hyperspectral data analysis to realize the full potential of spectral imaging. The strength of the software lies in its interactive features that enable the users to optimize parameters and obtain visual input for the user. The entire software can be operated without any prior programming skills allowing interactive sessions of raw and processed data. IDCube Lite, a free version of the software described in the paper, has many benefits compared to existing packages and offers structural flexibility to discover new hidden features. 

High-quality temperature data at a finer spatio-temporal scale is critical for analyzing the risk of heat exposure and hazards in urban environments. The variability of urban landscapes makes cities a challenging environment for quantifying heat exposure. Most of the existing heat hazard studies have inherent limitations on two fronts; first, the spatio-temporal granularities are too coarse, and second, the inability to track the ambient air temperature (AAT) instead of land surface temperature (LST). Overcoming these limitations requires developing models for mapping the variability in heat exposure in urban environments. We investigated an integrated approach for mapping urban heat hazards by harnessing a diverse set of high-resolution measurements, including both ground-based and satellite-based temperature data. We mounted vehicle-borne mobile sensors on city buses to collect high-frequency temperature data throughout 2018 and 2019. Our research also incorporated key biophysical parameters and Landsat 8 LST data into Random Forest regression modeling to map the hyperlocal variability of heat hazard over areas not covered by the buses. The vehicle-borne temperature sensor data showed large temperature differences within the city, with the largest variations of up to 10 °C and morning-afternoon diurnal changes at a magnitude around 20 °C. Random Forest modeling on noontime (11:30 am – 12:30 pm) data to predict AAT produced accurate results with a mean absolute error of 0.29 °C and successfully showcased the enhanced granularity in urban heat hazard mapping. These maps revealed well-defined hyperlocal variabilities in AAT, which were not evident with other research approaches. Urban core and dense residential areas revealed larger than 5 °C AAT differences from their nearby green spaces. The sensing framework developed in this study can be easily implemented in other urban areas, and findings from this study will be beneficial in understanding the heat vulnerabilities of individual communities. It can be used by the local government to devise targeted hazard mitigation efforts such as increasing green space, developing better heatsafety policies, and exposure warning for workers. 

Abstract India is located at a critical geographic crossroads for understanding the dispersal of Homo sapiens out of Africa and into Asia and Oceania. Here we report evidence for long-term human occupation, spanning the last ~80 thousand years, at the site of Dhaba in the Middle Son River Valley of Central India. An unchanging stone tool industry is found at Dhaba spanning the Toba eruption of ~74 ka (i.e., the Youngest Toba Tuff, YTT) bracketed between ages of 79.6 ± 3.2 and 65.2 ± 3.1 ka, with the introduction of microlithic technology ~48 ka. The lithic industry from Dhaba strongly resembles stone tool assemblages from the African Middle Stone Age (MSA) and Arabia, and the earliest artefacts from Australia, suggesting that it is likely the product of Homo sapiens as they dispersed eastward out of Africa. 

In September 2017, Hurricane Maria severely defoliated Puerto Rico's landscape, coinciding with a series of persistent hydrological consequences involving the atmospheric, terrestrial, and marine components of the water cycle. During the defoliated period, the atmosphere's thermodynamic structure more strongly explained daily cloud activity (R²_PRE = 0.02; R²_POST = 0.40) and precipitation (R²_PRE = 0.19; R²_POST = 0.33) than before landfall, indicating that post‐Maria land‐atmosphere interactions were comparatively muted, with similar precipitation patterns also found following Hurricanes Hugo (1989) and Georges (1998). Meanwhile, modeled post‐Maria runoff exceeded statistical expectations given the magnitude of contemporaneous precipitation. Enhanced runoff also coincided with greater sediment loads in nearshore waters, increasing sediment content greater than twofold. This study offers a holistic narrative of hydrospheric disturbance and recovery, whereby the instantaneous, large‐scale removal of vegetation is accompanied by hydrologic changes “upstream” in the atmosphere and “downstream” in rivers and estuaries.