Parameter and structural model imperfection propagation using evidence theory in land cover change prediction

Ferchichi, Ahlem; Boulila, ‪Wadii; Farah, Imed Riadh

doi:10.1109/ipas.2014.7043270

Cited by 3 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The LCC prediction model proposed in [53] used the ANN to derive the LCC rules, then, it used the CA model to simulate future scenarios. In general, input parameters (features extracted from satellite image objects) of LCC prediction model and the model structure (model itself) are marred by aleatory and epistemic uncertainties which affect the reliability of decision about these changes [1] [8] [9] [12]. Figure 4 illustrates the flowchart of the methodology applied during the study.…”

Section: Methodsmentioning

confidence: 99%

“…To illustrate the importance of propagating both uncertainty types through LCC prediction model, the analysis with pure aleatory uncertainty assumption is conducted where all 16 uncertain input parameters are treated as aleatory with normal probability distributions. In this case, the cumulative distribution function (CDF) of output representing only the uncertainty in input parameters is obtained via belief function theory based on equation (12). In fact, Figure 9 shows this distribution based on 10,000 samples.…”

Section: Propagating Model Parameter Uncertaintymentioning

confidence: 99%

See 1 more Smart Citation

Propagating aleatory and epistemic uncertainty in land cover change prediction process

Ferchichi

Boulila

Farah

2017

Ecological Informatics

Self Cite

View full text Add to dashboard Cite

An objective of satellite remote sensing is to predict or characterize the land cover change (LCC) over time. Sometimes we are capable of describing the changes of land cover with a probability distribution. However, we need sufficient knowledge about the natural variability of these changes, which is not always possible. In general, uncertainties can be subdivided into aleatory and epistemic. The main problem is that classical probability theory does not make a clear distinction between aleatory and epistemic uncertainties in the way they are represented, i.e., both of them are described with a probability distribution. The aim of this paper is to propagate the aleatory and epistemic uncertainty associated with both input parameters (features extracted from satellite image object) and model structure of LCC prediction process using belief function theory. This will help reducing in a significant way the uncertainty about future changes of land cover. In this study, the changes prediction of land cover in Cairo region, Egypt for next 16 years (2030) is anticipated using multi-temporal Landsat TM5 satellite images in 1987 and 2014. The LCC prediction model results indicated that 15% of the agriculture and 6.5% of the desert will be urbanized in 2030. We conclude that our method based on belief function theory has a potential to reduce uncertainty and improve the prediction accuracy and is applicable in LCC analysis.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Propagating Model Parameter Uncertaintymentioning

confidence: 99%