Geology Reports⌕ Search
Home/Archive/USGS

USGS · 70031043

Improving land resource evaluation using fuzzy neural network ensembles

Yue-Ju Xue·Y.-M. HU·S.-G. Liu·J.-F. YANG·Q.-C. CHEN·S.-T. BAO
View original source ↗Export metadata ↓

Abstract

Land evaluation factors often contain continuous-, discrete- and nominal-valued attributes. In traditional land evaluation, these different attributes are usually graded into categorical indexes by land resource experts, and the evaluation results rely heavily on experts' experiences. In order to overcome the shortcoming, we presented a fuzzy neural network ensemble method that did not require grading the evaluation factors into categorical indexes and could evaluate land resources by using the three kinds of attribute values directly. A fuzzy back propagation neural network (BPNN), a fuzzy radial basis function neural network (RBFNN), a fuzzy BPNN ensemble, and a fuzzy RBFNN ensemble were used to evaluate the land resources in Guangdong Province. The evaluation results by using the fuzzy BPNN ensemble and the fuzzy RBFNN ensemble were much better than those by using the single fuzzy BPNN and the single fuzzy RBFNN, and the error rate of the single fuzzy RBFNN or fuzzy RBFNN ensemble was lower than that of the single fuzzy BPNN or fuzzy BPNN ensemble, respectively. By using the fuzzy neural network ensembles, the validity of land resource evaluation was improved and reliance on land evaluators' experiences was considerably reduced. ?? 2007 Soil Science Society of China.

Explore related subjects

PedosphereArticle

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Yue-Ju Xue, Y.-M. HU, S.-G. Liu, J.-F. YANG, Q.-C. CHEN, S.-T. BAO. 2007. Improving land resource evaluation using fuzzy neural network ensembles. https://doi.org/10.1016/s1002-0160(07)60052-6

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related USGS reports

USGS2010

Soil quality assessment using weighted fuzzy association rules

Fuzzy association rules (FARs) can be powerful in assessing regional soil quality, a critical step prior to land planning and utilization; however, traditional FARs mined from soil quality database, ignoring the importance variability of the rules, can be redundant and far from optimal. In this study, we developed a method applying different weights to traditional FARs to improve accuracy of soil quality assessment. After the FARs for soil quality assessment were mined, redundant rules were eliminated according to whether the rules were significant or not in reducing the complexity of the soil quality assessment models and in improving the comprehensibility of FARs. The global weights, each representing the importance of a FAR in soil quality assessment, were then introduced and refined using a gradient descent optimization method. This method was applied to the assessment of soil resources conditions in Guangdong Province, China. The new approach had an accuracy of 87%, when 15 rules were mined, as compared with 76% from the traditional approach. The accuracy increased to 96% when 32 rules were mined, in contrast to 88% from the traditional approach. These results demonstrated an improved comprehensibility of FARs and a high accuracy of the proposed method.

Pedosphere↗
USGS2010

A spectral index for estimating soil salinity in the Yellow River Delta region of China using EO-1 Hyperion data

Soil salinization is one of the most common land degradation processes. In this study, spectral measurements of saline soil samples collected from the Yellow River Delta region of China were conducted in laboratory and hyperspectral data were acquired from an EO-1 Hyperion sensor to quantitatively map soil salinity in the region. A soil salinity spectral index (SSI) was constructed from continuum-removed reflectance (CR-reflectance) at 2 052 and 2 203 nm, to analyze the spectral absorption features of the salt-affected soils. There existed a strong correlation ( r =0.91) between the SSI and soil salt content (SSC). Then, a model for estimation of SSC with SSI was established using univariate regression and validation of the model yielded a root mean square error (RMSE) of 0.986 and an R 2 of 0.873. The model was applied to a Hyperion reflectance image on a pixel-by-pixel basis and the resulting quantitative salinity map was validated successfully with RMSE = 1.921 and R 2 =0.627. These suggested that the satellite hyperspectral data had the potential for predicting SSC in a large area.

Yellow River↗