A Biologically Interpretable Two-Stage Deep Neural Network (BIT-DNN) for Vegetation Recognition From Hyperspectral Imagery
Open Access
- 24 February 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892), 1-20
- https://doi.org/10.1109/tgrs.2021.3058782
Abstract
Spectral-spatial-based deep learning models have recently proven to be effective in hyper-spectral image (HSI) classification for various earth monitoring applications such as land cover classification and agricultural monitoring. However, due to the nature of ``black-box'' model representation, how to explain and interpret the learning process and the model decision, especially for vegetation classification, remains an open challenge. This study proposes a novel interpretable deep learning model--a biologically interpretable two-stage deep neural network (BIT-DNN), by incorporating the prior-knowledge (i.e., biophysical and biochemical attributes and their hierarchical structures of target entities)-based spectral-spatial feature transformation into the proposed framework, capable of achieving both high accuracy and interpretability on HSI-based classification tasks. The proposed model introduces a two-stage feature learning process: in the first stage, an enhanced interpretable feature block extracts the low-level spectral features associated with the biophysical and biochemical attributes of target entities; and in the second stage, an interpretable capsule block extracts and encapsulates the high-level joint spectral-spatial features representing the hierarchical structure of biophysical and biochemical attributes of these target entities, which provides the model an improved performance on classification and intrinsic interpretability with reduced computational complexity. We have tested and evaluated the model using four real HSI data sets for four separate tasks (i.e., plant species classification, land cover classification, urban scene recognition, and crop disease recognition tasks). The proposed model has been compared with five state-of-the-art deep learning models. The results demonstrate that the proposed model has competitive advantages in terms of both classification accuracy and model interpretability, especially for vegetation classification.Keywords
This publication has 47 references indexed in Scilit:
- Knowledge-based region labeling for remote sensing image interpretationComputers, Environment and Urban Systems, 2012
- Evaluation of Sentinel-2 Red-Edge Bands for Empirical Estimation of Green LAI and Chlorophyll ContentSensors, 2011
- Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: Modeling and validation in the context of precision agricultureRemote Sensing of Environment, 2004
- The photochemical reflectance index: an optical indicator of photosynthetic radiation use efficiency across species, functional types, and nutrient levelsOecologia, 1997
- Knowledge-Based Image Understanding Systems: A SurveyComputer Vision and Image Understanding, 1997
- The use of the Normalized Difference Water Index (NDWI) in the delineation of open water featuresInternational Journal of Remote Sensing, 1996
- Optimization of soil-adjusted vegetation indicesRemote Sensing of Environment, 1996
- Statistics Notes: Diagnostic tests 1: sensitivity and specificityBMJ, 1994
- The red edge position and shape as indicators of plant chlorophyll content, biomass and hydric status.International Journal of Remote Sensing, 1994
- Relation between the normalized difference vegetation index and ecological variablesRemote Sensing of Environment, 1991