Reason: Final chapter of the thesis is pending manuscript development.
until file(s) become available
Machine Learning based High-Throughput Phenotyping Framework for Crop Yield Prediction using Unmanned Aircraft Systems
This dissertation aims at utilizing UAS data to develop a machine learning based high-throughput phenotyping framework for crop yield estimation. In this research, plant parameters such as canopy height (CH), canopy cover (CC), canopy volume (CV), normalized difference vegetation index (NDVI), and excessive greenness index (ExG) were extracted from fine spatial resolution UAS based RGB and multispectral images collected weekly throughout the growing season. Initially, a comparative study was conducted to compare two management practices in cotton: conventional tillage (CT) and no-tillage (NT). This initial study was designed to test the reliability of the UAS derived plant parameters, and results revealed a significant difference in cotton growth under CT and NT. Unlike manual measurements, which rely on limited samples, UAS technology provided the capability to exploit the entire population, which makes UAS derived data more robust and reliable. Additionally, an inter-comparison study was designed to compare CC derived from RGB and multispectral data over multiple flights during the growing season of the cotton crop. After assessing the reliability of UAS derived canopy parameters, a novel machine learning framework was developed for cotton yield estimation using multi-temporal UAS data. This study reveals that UAS derived multi-temporal data along with non-temporal and qualitative data can be combined within a machine learning framework to provide a reliable crop yield estimation.
UAS technology is proven to be robust and reliable. It efficiently works over small-size research fields or breeding trial fields. However, extensive aerial coverage using UAS is not practically feasible. Alternatively, satellite images have the advantage of covering a vast area, but they provide coarser spatial resolution data. To overcome the limitation of UAS and satellite sensors, this study explored deep learning-based methodologies to incorporate UAS derived canopy attributes as additional information to improve the satellite-based yield estimation. Additionally, the generalization capability of the proposed models was demonstrated by training on one experiment field and predicting crop yield for another field.