|
Author/s | Year | Objective | Method | Location | Results |
|
Tong [40] | 2016 | Planning and management of building layout in green zones | GA | Yuhuatai and Qingliangshan Parks in Nanjing (China) | IOD is the only criterion used for assessing results |
Naghibi et al. [41] | 2016 | Predicting urban growth from satellite images | CA + artificial bee colony | Urmia (Iran) | Overall accuracy: 90.1% |
Feng et al. [31] | 2016 | Predicting urban growth from satellite images | CA + LS-SVM | Shanghai Qingpu-Songjiang (China) | Maximum accuracy of 81.2% in the 16th iteration |
Perez-Molina et al. [42] | 2017 | Simulation of urban growth scenarios and their consequent flooding | CA | Kampala (Uganda) | Overall accuracy: 97% y 98%. Edge index differential of 0.10 (with a land-cover map index of 49.05) |
Chen et al. [43] | 2017 | Simulation of urban land changes | LP-CA | Shenzhen (China) | Higher average accuracy: 73.08%. Coefficients of correlation of 0.902, 0.883, and 0.881 between the industrial, residential, and commercial land change areas observed and simulated |
Jat et al. [44] | 2017 | Predicting urban growth from satellite images | CA (SLEUTH model) | Ajmer, Rajasthan (India) | Overall accuracy: 80% urban area, 83% urban borders, and 60% for urban clusters |
Li et al. [45] | 2017 | Predicting urban growth from satellite images | Segmentation-Patch-CA | Guangzhou (China) | Overall accuracy: 96% |
Liu et al. [46] | 2017 | Future land-use simulation (FLUS) | CA + ANN | China | Overall accuracy: 84.7% |
Feng and Tong [47] | 2018 | Predicting urban growth from geometric maps and satellite images | DE-CA | Kunming (China) | Overall accuracy: 92.4% |
Traore et al. [48] | 2018 | Predicting urban growth from satellite images | CA-Markov | Conakry (Guinea) | Overall accuracy: 92% |
Pazos-pérez et al. [49] | 2018 | Prediction of urban vertical growth | GA + EC | Minato, Tokyo (Japan) | Overall accuracy number of buildings: 100%, with a 19.5% deviation in building height |
Fu et al. [50] | 2018 | Land-use simulation | CA-Markov | Hamilton County, Ohio (USA) | Overall accuracy: 91,07% |
Feng et al. [51] | 2018 | Land-use simulation | CA + GA | Yangtze River Delta (China) | Overall accuracy: 88% |
CA + PSO |
CA + GSA |
CA + LR |
Lipinget al. [52] | 2018 | Land-use simulation | CA-Markov | Jiangle (China) | Overall accuracy: 92.33% |
He et al. [53] | 2018 | Predicting urban growth and land-use simulation | CA + UMCNN | Pearl River Delta (China) | Overall accuracy: >93% |
Yuliantoe et al. [54] | 2019 | Land-use simulation | CA-Markov | Citarum Watershed, West Java (Indonesia) | Overall accuracy in the most optimistic scenario: merit figure 72.5%, accuracy of producer 78.5%, and accuracy of user 79.6% |
Lu and Wu [55] | 2019 | Land-use simulation | CA-Markov | Hefei (China) | Overall accuracy: 90,48%, 87,76%, 85,1%, and y 82,36%, for the 3-, 5-, 10-, and 15-year intervals, respectively |
Devendran and Lakshmanan [56] | 2019 | Predicting urban growth from satellite images | CA-Markov + NNACA | Chennai (India) | Overall accuracy: 84% |
Huang et al. [57] | 2020 | Land-use simulation | CA-Markov | Beijing (China) | Relative error on construction land <0.3% |
Khawaldah et al. [58] | 2020 | Land-use simulation | CA-Markov | Irbid (Jordan) | Overall accuracy: 78.4% |
Mohamed and Worku [59] | 2020 | Land-use simulation | CA-Markov | Addis Ababa (Ethiopia) | Overall accuracy: 87% |
Nurwanda & Honjo [60] | 2020 | Prediction of urban growth and land surface temperature | ANN-Markov | Bogor City (Indonesia) | Overall accuracy >90% |
Anand & Oinam [61] | 2020 | Land-use simulation | ANN-Markov | Manipur River (India) | Overall accuracy: 88%–93% |
Mansour et al. [62] | 2020 | Predicting urban growth from satellite images and land-use simulation | CA-Markov | Nizwa, Al Dakhiliyah, (Oman) | Overall accuracy >80% |
|