COMPARING ANN AND CART TO MODEL MULTIPLE LAND USE CHANGES: A CASE STUDY OF SARI AND GHAEM-SHAHR CITIES IN IRAN

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

AHMADLOU M.; DELAVAR M.R.; TAYYEBI A.

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Journal Paper

Paper Information

Journal: JOURNAL OF GEOMATICS SCIENCE AND TECHNOLOGY Year:2016 | Volume:6 | Issue:1 Page(s): 292-303

Download Full-Text

Persian Verion

View:

1,195

Download:

Cites:

Information Journal Paper

Title

COMPARING ANN AND CART TO MODEL MULTIPLE LAND USE CHANGES: A CASE STUDY OF SARI AND GHAEM-SHAHR CITIES IN IRAN

Author(s)

AHMADLOU M. | DELAVAR M.R. | TAYYEBI A. | Issue Writer Certificate

Keywords

CLASSIFICATION AND REGRESSION TREEQ2

ARTIFICIAL NEURAL NETWORKQ2

VARIABLE IMPORTANCE INDEXQ2

MULTIPLE LAND USE CHANGESQ2

RECEIVER OPERATING CHARACTERISTICQ2

TOTAL OPERATING CHARACTERISTICSQ2

Abstract

Most of the land use change modelers have used to model binary land use change rather than MULTIPLE LAND USE CHANGES. As a first objective of this study, we compared two well-known LUC models, called CLASSIFICATION AND REGRESSION TREE (CART) and ARTIFICIAL NEURAL NETWORK (ANN) from two groups of data mining tools, global parametric and local non-parametric models, to model multiple LUCs. The case study is located in the north of Iran including cities of Sari and QaemShahr. Urban and agricultural changes over a period of 22 years between 1992 and 2014 have been model. Results showed that CART and ANN were effective tools to model multiple LUCs. While it was easier to interpret the results of CART, ANN was more effective to model multiple LUCs. In earlier studies, despite using CART, the extraction of effective factors of LUCs using a precise index has not been considered efficiently. As a second objective, this study performed a sensitivity analysis using VARIABLE IMPORTANCE INDEX to identify significant drivers of LUCs. While ANN was a black box for sensitivity analysis, CART identified significant delivers of LUCs easy. The results showed that the most important factors were distance from urban areas and rivers while aspect was the least effective factor. As a third or final objective of this study, the recently modified version of RECEIVER OPERATING CHARACTERISTICs (ROC) called total operating characteristic (TOC) as well as ROC were used for accuracy assessment of CART and ANN. The area under the ROC curves were 78% and 75% for urban changes for ANN and CART models, respectively. The area under the ROC curves were 72% and 65% for agricultural changes for ANN and CART models, respectively. We found that although TOC and ROC were similar to each other, TOC proved more informative than conventional ROC as a goodness-of-fit metric. The outcome of this study can assist planners and managers to provide sustainability in natural resources and in developing a better plan for future given the needs to understand those contributing factors in urban and agriculture changes.

Cites

No record.

References

No record.

Cite

APA: Copy

AHMADLOU, M., DELAVAR, M.R., & TAYYEBI, A.. (2016). COMPARING ANN AND CART TO MODEL MULTIPLE LAND USE CHANGES: A CASE STUDY OF SARI AND GHAEM-SHAHR CITIES IN IRAN. JOURNAL OF GEOMATICS SCIENCE AND TECHNOLOGY, 6(1), 292-303. SID. https://sid.ir/paper/249480/en

Vancouver: Copy

AHMADLOU M., DELAVAR M.R., TAYYEBI A.. COMPARING ANN AND CART TO MODEL MULTIPLE LAND USE CHANGES: A CASE STUDY OF SARI AND GHAEM-SHAHR CITIES IN IRAN. JOURNAL OF GEOMATICS SCIENCE AND TECHNOLOGY[Internet]. 2016;6(1):292-303. Available from: https://sid.ir/paper/249480/en

IEEE: Copy

M. AHMADLOU, M.R. DELAVAR, and A. TAYYEBI, “COMPARING ANN AND CART TO MODEL MULTIPLE LAND USE CHANGES: A CASE STUDY OF SARI AND GHAEM-SHAHR CITIES IN IRAN,” JOURNAL OF GEOMATICS SCIENCE AND TECHNOLOGY, vol. 6, no. 1, pp. 292–303, 2016, [Online]. Available: https://sid.ir/paper/249480/en

Related Journal Papers