Open Access Open Access  Restricted Access Subscription or Fee Access

Real-time Landslide Early Warning System Based on Fuzzy Ad Hoc Data Covering Methods Using Empirically-based Model

Amir Mustofa Irawan, Hapsoro Agung Nugroho, Onno Widodo Purbo, Sandy Tri Gustono, Desak Putu Okta Veanti, Munawar, Rikha Rizki Mahmudiah

Abstract



In this research, we take a different approach to build a new landslide warning system by using the fuzzy rule-based system (FRBS) model rather than either satellite remote sensing or dynamical approach that was employed in most landslides warning studies. This fuzzy model was developed based on ad hoc data covering methods and empirically-based model. In this case, fuzzy rules were set by learning from numerical data. We found the model satisfactorily simulated the occurrence of landslide with values of area under the Fuzzy Receiver Operating Characteristic (ROC) curve at 0.825 (range: 0 to 1, perfect score: 1) resulting in a good agreement with the occurrence of landslide data obtained from the Indonesian National Agency for Disaster Management (BNPB). For the domain research, this warning system is developed at Banjarnegara, Central Java, Indonesia, which chosen as an example of a populated highland that is highly vulnerable to landslides. In this system, Soil Moisture Index (SMI) was calculated based on a regolith-moisture model to represent the soil moisture conditions. Besides, the empirical intensity-duration (ID) threshold and cumulative rainfall threshold (CT) have been calculated as an empirically-based model. They were derived on a numerical basis, starting from a database of 141 shallow landslides from 2011 to 2017. Fuzzy ROC analysis was employed to validate an FRBS based on continuous time series of newest rainfall and evapotranspiration data and landslide database from 2018 to 2019. Ultimately, the Fuzzy model could simulate the gold standard of the landslide alert system with small error measures.

Keywords


landslides, early warning, fuzzy rule-based system, roc curve.

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.