Modeling landslide-prone zones that provide key information in the form of landslide-prone locations is the first step in a landslide disaster risk assessment. This zoning is useful in supporting disaster risk management efforts, regional spatial planning, as well as in realizing regional resilience to landslide disasters. Related to the diversity, dynamics, and complexity of the factors that cause landslides (topographical, geological, climatological, and anthropogenic), the development of approaches in accurate landslide hazard modeling continues to develop. This makes landslide-prone modeling part of the big data issue (data that is complex, heterogeneous, and in large quantities), which has its own challenges in processing with traditional statistical methods. In this regard, this research takes advantage of the rapid development of Artificial Intelligence (AI) technology in modeling landslide-prone zones, especially with Machine Learning (ML) and Deep Learning (DL) methods. Even though it has great potential benefits, the use of AI in landslide vulnerability research in Indonesia is still not widely carried out, especially in study locations that have a high frequency of landslide events. In this regard, this study aims to: (1) examine the factors that influence the occurrence of landslides, (2) model landslide-prone zones with various approaches in artificial intelligence technology, (3) evaluate the performance of AI technologies (such as ML and DL). in producing a landslide-prone zone model, and (4) assessing the risk of landslides in the study location, on the related socio-physical vulnerability aspects. On the other hand, the traditionalarchitecture phenomena closely related to ideas in the field of mathematics.

Modeling, Artificial Intelligence, Learning Mathematics

• Dr. Anita Rahayu, S.Si., M.Si.

• Suwarno, S.Si., M.Pd.

• Dr. Samsul Arifin, S.Si., M.Sc.

• Muhammad Amien Ibrahim, S.Kom., M.Sc.

• Abram Setyo Prabowo, S.Kom, M.Cs.