Attributes of neural networks for extracting continuous vegetation variables from optical and radar measurements

• Published in: International journal of remote sensing 1998-01, Vol.19 (14), p.2639-2663
• Main Authors: KIMES, D. S, NELSON, R. F, MANRY, M. T, FUNG, A. K
• Format: Article
• Language: English
• Subjects: Applied geophysics; Earth sciences; Earth, ocean, space; Exact sciences and technology; Internal geophysics
• ISSN: 0143-1161; 1366-5901
• DOI: 10.1080/014311698214433

Efficient algorithms that incorporate different types of spectral data and ancillary data are being developed to extract continuous vegetation variables. Inferring continuous variables implies that functional relationships must be found among the predicted variable(s), the remotely sensed data and the ancillary data. Neural networks have attributes which facilitate the extraction of vegetation variables. The advantages and power of neural networks for extracting continuous vegetation variables using optical and/or radar data and ancillary data are discussed and compared to traditional techniques. Studies that have made advances in this research area are reviewed and discussed. Neural networks can provide accurate initial models for extracting vegetation variables when an adequate amount of data is available. Networks provide a performance standard for evaluating existing physically based models. Many practical problems occur when inverting physically based models using traditional techniques and neural network techniques can provide a solution to these problems. Networks can be used as a tool to find a set of variables relevant to the desired variables to be inferred for measurement and modelling studies. Neural networks adapt to incorporate new data sources that would be difficult or impossible to use with conventional techniques. Neural networks employ a more powerful and adaptive nonlinear equation form as compared to traditional linear and simple nonlinear analyses. This power and flexibility is gained by repeating nonlinear activation functions in a network structure. This unique structure allows the neural network to learn complex functional relationships between the input and output data that cannot be envisioned by a researcher.