Estimation of photosynthetic efficiency for monitoring seagrass health using neural networks

Photosynthetic efficiency is a measure of plant stress that can be used very effectively to monitor the health of marine plants like seagrasses. However in situ measurements of the photosynthetic efficiency of seagrasses are time consuming and expensive. In this paper, neural network-based models are developed to estimate photosynthetic efficiency from field measured spectral reflectance data. Variable selection based on correlation analysis and dimension reduction based on principal component analysis are used for data preprocessing. The significance of the proposed neural network-based approach is that it can model the unknown non-linear relationship between photosynthetic efficiency and spectral reflectance measurements without requiring any prior knowledge of their inherent relationship. The goal is to develop a reliable neural network-based model, which can be extended for application to remotely sensed spectral reflectance data thereby enabling aerial or satellite monitoring of seagrass health.