Harsha Vardhan Kaparthi
My name is Harsha Vardhan Kaparthi, an Indian citizen, currently pursuing the PhD program in Italy. I am a dedicated engineer with a strong focus on orbital mechanics and earth observation. I am currently residing in Trento, Italy, I have a Master’s degree in Engineering from Sapienza University of Rome, where I graduated with a final grade of 103/110. My master's thesis, titled "Numerical Analysis on the Stability of Relative Motion in the presence of Perturbations," explored the relative motion of spacecraft in close proximity, considering harmonic perturbations and impulsive maneuvers.
Prior to my master's degree, I completed a Bachelor of Technology at Jawaharlal Nehru Technological University Hyderabad, India, achieving a final grade of 77.01%. My undergraduate thesis examined the effects of quenching and partitioning in carbon steels and tool steels, showcasing the ability to engage with complex engineering concepts.
In addition to my academic accomplishments, I gained practical experience during my apprenticeship at the National Skill Training Institute in Hyderabad, India, where I completed an advanced training course in automotive fuel systems in internal combustion engines.
I am proficient in multiple languages, including Telugu (native), English (C1), Hindi (C1), and has intermediate knowledge (A2 level) of Italian language. I have strong digital skills, being adept in various software tools such as Microsoft Office, AutoCAD, CATIA V5, ANSYS Workbench CFD, MATLAB, and Simulink, along with foundational knowledge in programming languages like C, C++, Java, and Python.
As an aspiring engineer, I am aiming to secure a challenging position that leverages my technical expertise and fosters innovation. I am committed to utilizing my skills to contribute meaningfully to projects while being recognized for my hard work, honesty, and sincerity.
Sessions
This study presents an integrated data preprocessing framework tailored to monitor peatland degradation across diverse climate zones, leveraging the high-resolution capabilities of hyperspectral imagery, Synthetic Aperture Radar (SAR), and LiDAR data. Peatlands are vital carbon sinks that face threats from environmental changes and human activities, making their effective monitoring critical. However, differences in climate and ecosystem characteristics across peatland zones, from temperate to boreal, pose unique challenges in data integration and preprocessing. We address these by aligning multi-sensor data sources to enable seamless analysis of peatland degradation patterns.
To capture intricate peatland features, we incorporate spectral bands from hyperspectral sensors, SAR data for moisture and structural insights, and LiDAR data to detail elevation and topographic changes. Our data integration strategy harmonizes these data layers, facilitating a multi-dimensional view of peatland health. Furthermore, preprocessing steps are adapted based on climate zone characteristics, accounting for variations in spectral reflectance, moisture content, and vegetation structure typical of each zone. This climate-sensitive approach addresses issues in standardizing data resolution and spectral calibration, enhancing the accuracy of degradation assessments.
To streamline the high-dimensional data and retain critical spectral information, we utilize autoencoders and deep autoencoders. These deep learning models effectively reduce data complexity, extracting essential spectral signatures that characterize peatland degradation indicators without significant information loss. This approach ensures a rich yet manageable dataset that supports fine-grained analysis across different peatland types.
Overall, this framework provides a robust foundation for analyzing peatland degradation, offering climate-specific, high-resolution insights critical for conservation and sustainable land management. By enhancing peatland monitoring across diverse environmental conditions, the proposed methodology facilitates more informed decision-making in peatland preservation efforts.