Analysing performance of SLEUTH model calibration using brute force and genetic algorithm-based methods

被引：13

作者：

Saxena, Ankita ^{[1
]}

Jat, Mahesh Kumar ^{[1
]}

机构：

[1] Malaviya Natl Inst Technol Jaipur, Dept Civil Engn, Jaipur 302017, Rajasthan, India

来源：

GEOCARTO INTERNATIONAL | 2020年 / 35卷 / 03期

关键词：

Urban growth; SLEUTH; cellular automata; brute force; genetic algorithm; LAND-USE-CHANGE; CELLULAR-AUTOMATA; URBAN-GROWTH; SIMULATION; EVOLUTION; SYSTEMS; AGENTS; COVER; CITY;

D O I：

10.1080/10106049.2018.1516242

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

Present study is aimed to compare the performance of SLEUTH model from two different calibration methods, that is, brute force and GA in term of computational efficiency of calibration processes, capturing urban growth, a form of growth or growth pattern and its spatial distribution. SLEUTH has been parameterized for Ajmer city (India) and its performance has been compared in term of eight parameters/methods, that is, computational efficiency, model fitness that is, OSM, urban shape index, best fit coefficient values, hit-miss-false alarm method, kappa statistics, accuracy percentage and visual analysis. GA-based calibration has been found to be computationally more efficient and relatively better in capturing urban growth and form of growth as compared to brute force. Brute force calibration seems to be slightly better considering urban hits as compared to GA, however, GA is better with respect to lesser false alarms.

引用

页码：256 / 279

页数：24

共 50 条

[31] Genetic algorithm-based combinatorial parametric optimization for the calibration of microscopic traffic simulation models
Ma, T
Abdulhai, B
2001 IEEE INTELLIGENT TRANSPORTATION SYSTEMS - PROCEEDINGS, 2001, : 848 - 853
[32] Water management using genetic algorithm-based machine learning
Gino Sophia, S. G.
Ceronmani Sharmila, V.
Suchitra, S.
Sudalai Muthu, T.
Pavithra, B.
SOFT COMPUTING, 2020, 24 (22) : 17153 - 17165
[33] Teaching Genetic Algorithm-based Parameter Optimization Using Pacman
Silla, Carlos N., Jr.
2016 IEEE FRONTIERS IN EDUCATION CONFERENCE (FIE), 2016,
[34] Water management using genetic algorithm-based machine learning
S. G. Gino Sophia
V. Ceronmani Sharmila
S. Suchitra
T. Sudalai Muthu
B. Pavithra
Soft Computing, 2020, 24 : 17153 - 17165
[35] Genetic Algorithm-Based Routing Performance Enhancement in Wireless Sensor Networks
Muruganantham, Naveen
El-Ocla, Hosam
2018 IEEE 3RD INTERNATIONAL CONFERENCE ON COMMUNICATION AND INFORMATION SYSTEMS (ICCIS), 2018, : 79 - 82
[36] Investigating the performance of genetic algorithm-based software test case generation
Berndt, DJ
Watkins, A
EIGHTH IEEE INTERNATIONAL SYMPOSIUM ON HIGH ASSURANCE SYSTEMS ENGINEERING, PROCEEDINGS, 2004, : 261 - 262
[37] Anomaly Classification Using Genetic Algorithm-Based Random Forest Model for Network Attack Detection
Assiri, Adel
CMC-COMPUTERS MATERIALS & CONTINUA, 2021, 66 (01): : 767 - 778
[38] Top-N Recommender Systems Using Genetic Algorithm-Based Visual-Clustering Methods
Marung, Ukrit
Theera-Umpon, Nipon
Auephanwiriyakul, Sansanee
Symmetry-Basel, 2016, 8 (07):
[39] A Genetic Algorithm-based Feature Selection Method for Human Identification based on Ground Reaction Force
Xu, Su
Zhou, Xu
Sun, Yi-ning
WORLD SUMMIT ON GENETIC AND EVOLUTIONARY COMPUTATION (GEC 09), 2009, : 665 - 669
[40] Calibration of Xinanjiang model parameters using hybrid genetic algorithm based fuzzy optimal model
Wang, Wen-Chuan
Cheng, Chun-Tian
Chau, Kwok-Wing
Xu, Dong-Mei
JOURNAL OF HYDROINFORMATICS, 2012, 14 (03) : 784 - 799

← 1 2 3 4 5 →