2021
DOI: 10.1007/s11069-021-04860-0
|View full text |Cite
|
Sign up to set email alerts
|

Exploring the sample size and replications scenarios effect on spatial prediction of flood, using MARS and MaxEnt methods case study: saliantape catchment, Golestan, Iran

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
6
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
6

Relationship

1
5

Authors

Journals

citations
Cited by 7 publications
(6 citation statements)
references
References 57 publications
0
6
0
Order By: Relevance
“…Boyce's index measures whether the values of suitability predicted by the model differ from chance alone. To estimate AUC, we used the ‘subsampling’ (jackknife) procedure in Maxent: 80% percent of the data were used for model calibration and the remaining 20% for model validation (Santini et al 2021; Rajabi et al 2021, ). The partial ROC analysis was conducted using the Niche toolbox package in R (Peterson et al 2008).…”
Section: Methodsmentioning
confidence: 99%
“…Boyce's index measures whether the values of suitability predicted by the model differ from chance alone. To estimate AUC, we used the ‘subsampling’ (jackknife) procedure in Maxent: 80% percent of the data were used for model calibration and the remaining 20% for model validation (Santini et al 2021; Rajabi et al 2021, ). The partial ROC analysis was conducted using the Niche toolbox package in R (Peterson et al 2008).…”
Section: Methodsmentioning
confidence: 99%
“…All models were trained with a random subset of 80% of the presence locations and evaluated with the remaining 20%, repeated five times each. We chose this proportion of training/testing data to maximize the data available for model training while still preserving a sizable dataset for model evaluation, and it has proven an effective ratio in previous evaluations of cross‐validation data proportioning (Rajabi et al, 2021). Models were tested for predictive accuracy with the area under the receiver operating curve (AUC) and maximum true skill statistic (TSS), and parsimony with AICc (Allouche et al, 2006; Burnham & Anderson, 2004).…”
Section: Methodsmentioning
confidence: 99%
“…All models were trained with a random subset of 80% of the presence locations and evaluated with the remaining 20%, repeated five times each. We chose this proportion of training/testing data to maximize the data available for model training while still preserving a sizable dataset for model evaluation, and it has proven an effective ratio in previous evaluations of cross-validation data proportioning (Rajabi et al, 2021).…”
Section: Habitat Suitability Modellingmentioning
confidence: 99%
“…A total of 217,000 people were affected by this flood. Approximately 387 villages and 4000 buildings were severely damaged (Ministry of Agriculture – Jihad, 2006; Rahmati et al, 2016; Rajabi et al, 2021).…”
Section: Introductionmentioning
confidence: 99%