Assessment of crops healthiness via deep learning approach: Python / Mohamad Amirul Asyraf Mohd Ramli

Mohd Ramli, Mohamad Amirul Asyraf (2023) Assessment of crops healthiness via deep learning approach: Python / Mohamad Amirul Asyraf Mohd Ramli. [Student Project] (Submitted)
Abstract

Detecting healthy crops using Python in the context of an analysis project has emerged as an approach that speeds up a process to find out the current state of crops. This study focuses on using Python for remote sensing data analysis to identify and classify healthy crops. By leveraging image processing techniques, statistical analysis and machine learning algorithms, Python enables the extraction of relevant features and patterns from data. This feature includes spectral information, vegetation indices and other quantitative metrics that indicate plant health. This study addresses challenges related to data acquisition, preprocessing, feature extraction, and results. The importance of this study lies in its potential to provide an accurate and efficient algorithm for plant health assessment, in making informed decisions. By using Python in analytics projects, farmers can identify areas of concern, monitor crop health trends, and implement targeted interventions to optimize resource use and maximize yields. This research utilizing the Python programming language and the PyCharm integrated development environment (IDE) to integrate coding into the processing. This research utilized several libraries in PyCharm, including NumPy, Rasterio, and Matplotlib. Furthermore, these libraries provide an essential functionalities for data processing and visualization tasks .These findings emphasize the importance of a data-driven approach and the integration of Python in analytical projects helping to better crop management practices, increased sustainability and increased productivity in the agricultural sector.

Item Details
Edit Item
Edit Item
Downloads & Files
[thumbnail of 87930.pdf]
Text
87930.pdf
Download (136kB)
Location & Physical Holdings
Digital Copy
Physical Location
Item Status
Indexing & Metrics