Accuracy assessments of land use change simulation based on Markov-cellular automata model

• DOI: 10.1016/j.proenv.2012.01.117
• Publication Date: 2012-03-10T10:23:36Z
• Authors: S.Q. Wang; X.Q. Zheng; X.B. Zang
• Keywords: land use change simulation; Accruacy assessment; Markov-cellular automata model; 15. Life on land; 01 natural sciences; 0105 earth and related environmental sciences

The potential of Markov-cellular automata model has been recognized and used widely in land use changes simulation forecast, but previous researchers focused on analysis future result change. Few thoughts have given to the modal accuracy uncertainty assessments largely conducted by simply calculating overall value selected metric. To increase applied assessment Markov- cellular model, we explored through calculation Kappa index for location quantity. case study area was Changping District, which is a rapidly growing Beijing. We classified 1988 1995 TM image into six types accordance with Chinese standards. Computed transition suitable atlas based different range measurement units physical socioeconomic factors. And then, integrated these datasets simulate 2000 change map model. Lastly, analyzed assess cell size neighbour various kappa index. results showed that small better than big although it takes substantial amount time run. However, prediction quite stable sizes from 3*3 13*13. These allowed us understand what how factor including affected select best simulation.