| 2004 
  
n-File 
e.html 
APPLICATION OF ARTIFICIAL NEURAL NETWORK TECHNOLOGY 
IN WATER COLOR REMOTE SENSING INVERSION OF INLAND WATER BODY 
USING TM DATA 
J. P. Wang’, S. T. Cheng, H. F. Jia 
The Department of Environmental Science and Engineering, Tsinghua University, 100084, Beijing, China 
Wjp00(@mails.tsinghua.edu.en 
KEY WORDS: Artificial Neural Network Model, Water Color Remote Sensing, Extraction, Lake, Landsat Image 
ABSTRACT: 
For water color remote sensing study of inland water body, terrestrial satellite is often a good data source, because it has high spatial 
resolution. However, the precision of water color remote sensing inversion limits its application to water environmental monitoring 
and pollution analysis. This paper firstly studied traditional regression arithmetic and found that it was difficult to extract a good 
combination to construct the regression model. In order to acquire good inversion results, the paper introduced an advanced 
nonlinear science, artificial neural network technology. On the basis of satellite synchronous monitoring experiment, a BP neural 
network model was constructed to inverse SS, CODymn, DO, T-N, T-P and chl-a from Landsat TM data. The accuracy was acceptable 
and the relative error could be controlled below 25%. Moreover, the reasons of simulating error, ways of improving model and 
applications of the model were also analyzed in details. The result of this research showed that based on a small-scale of satellite 
synchronous experiment, the model could be applied successfully in investigation, analysis and estimation of water quality. 
It comes through long time that water quality data collection 
often depends on traditional monitoring, which needs much 
time and labor. So it is impossible to realize real-time and quick 
data acquiring. Along with continuous 
environmental information technology, water color remote 
sensing is applied more and more widely in the water quality 
monitoring of oceanic, coastal and inland water body because it 
has many advantages, such as wide range, synchronization and 
low cost of data collecting (Campbell, 1988; Claudia, 2001; 
Zhao, 2000). However, in order to utilize water color remote 
sensing technology more deeply and widely, there are many 
aspects to be improved: water color remote sensor technology, 
atmospheric correction and inversing model, which are in 
accordance with many scientific fields, and this paper paid 
more attention to inversing arithmetic study. 
1. OVERVIEW 
Researches of water color remote sensing began at 1920s, 
which had given correct explanation of sea color and begun to 
study optical field of water body (Shuleikin, 1933). But only 
after spatial technology occurred, water color remote sensing 
developed truly and quickly. Morel & Prieur classified water 
body as two types: Case | water body, which is Open Ocean; 
Case II water body, which is coastal, estuary and inland water 
body (Morel, 1977). Now the inversion research of Case I water 
body is correspondingly mature and the accuracy of inversing 
model is relatively good, since which component is mainly 
chlorophyll and has little suspended solids (SS). And that of 
Case II water body is very difficult due to the interaction of 
many water components, such as SS, chlorophyll and yellow 
Substance. Inversion research of Case II water body is a hot 
issue currently. Aiming at Case II water body inversion model, 
  
Corresponding author. 
development of 
677 
both theoretical model (Bricaud, 1986; Cheng, 2002) and 
empirical model (Chen, 1996; Ekstrand, 1992; Kuang, 2002) is 
getting along in recent years. And TM or ETM data was used 
by most researches (Chen, 1996; Cheng, 2002; Zhan, 2000). At 
present, the theoretical research still cannot be applied to 
practical inversion, but it can provide useful information to 
direct and modify empirical inversion arithmetic. Empirical 
model is often the main choice of quantitative calculation. How 
to improve its precision has become a key issue. 
Water color remote sensing satellites, such as SeaWiFS and 
OCTS, have high spectral resolution and good optical attributes 
of water body, which are ideal data sources for water color 
remote sensing research, but in practice, the small spatial 
resolution often limits their application in inland water body. 
Terrestrial remote sensing satellites, such as landsat7, which has 
good spatial resolution (about 30meters), is often adopted as 
data sources, but spectral resolution of terrestrial satellite is a 
little low and can't reflect optical attributes of water body well. 
All these reasons make it more difficult to identify suspended 
solids, chlorophyll and yellow substances, and also limit the 
application of water color remote sensing in inland water bodies. 
Artificial neural network (ANN) technology is a kind of 
nonlinear science developed from 1980's, which tries to 
simulate some basic attributes of people, such as self-adapting, 
self-organizing and fault tolerance. ANN has been used in many 
fields, such as mode identification and system simulation. 
Integrating water color remote sensing and characteristics of 
ANN, the paper hoped that artificial neural network model 
could perform the research of water color remote sensing 
inversion well. For all these, the paper drew the following 
research plan (Figure 1).