A Critical Review of Spatial Predictive Modeling Process in Environmental Sciences with Reproducible Examples in R
Spatial predictive methods are increasingly being used to generate predictions across various disciplines in environmental sciences. Accuracy of the predictions is critical as they form the basis for environmental management and conservation. Therefore, improving the accuracy by selecting an appropr...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-05-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/9/10/2048 |
_version_ | 1811338051263135744 |
---|---|
author | Jin Li |
author_facet | Jin Li |
author_sort | Jin Li |
collection | DOAJ |
description | Spatial predictive methods are increasingly being used to generate predictions across various disciplines in environmental sciences. Accuracy of the predictions is critical as they form the basis for environmental management and conservation. Therefore, improving the accuracy by selecting an appropriate method and then developing the most accurate predictive model(s) is essential. However, it is challenging to select an appropriate method and find the most accurate predictive model for a given dataset due to many aspects and multiple factors involved in the modeling process. Many previous studies considered only a portion of these aspects and factors, often leading to sub-optimal or even misleading predictive models. This study evaluates a spatial predictive modeling process, and identifies nine major components for spatial predictive modeling. Each of these nine components is then reviewed, and guidelines for selecting and applying relevant components and developing accurate predictive models are provided. Finally, reproducible examples using <i>spm</i>, an R package, are provided to demonstrate how to select and develop predictive models using machine learning, geostatistics, and their hybrid methods according to predictive accuracy for spatial predictive modeling; reproducible examples are also provided to generate and visualize spatial predictions in environmental sciences. |
first_indexed | 2024-04-13T18:04:14Z |
format | Article |
id | doaj.art-0b67ca3d604645a2bce5e3bbec305bb7 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-04-13T18:04:14Z |
publishDate | 2019-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-0b67ca3d604645a2bce5e3bbec305bb72022-12-22T02:36:06ZengMDPI AGApplied Sciences2076-34172019-05-01910204810.3390/app9102048app9102048A Critical Review of Spatial Predictive Modeling Process in Environmental Sciences with Reproducible Examples in RJin Li0National Earth and Marine Observations Branch, Environmental Geoscience Division, Geoscience Australia, Canberra 2601, Australian Capital Territory, AustraliaSpatial predictive methods are increasingly being used to generate predictions across various disciplines in environmental sciences. Accuracy of the predictions is critical as they form the basis for environmental management and conservation. Therefore, improving the accuracy by selecting an appropriate method and then developing the most accurate predictive model(s) is essential. However, it is challenging to select an appropriate method and find the most accurate predictive model for a given dataset due to many aspects and multiple factors involved in the modeling process. Many previous studies considered only a portion of these aspects and factors, often leading to sub-optimal or even misleading predictive models. This study evaluates a spatial predictive modeling process, and identifies nine major components for spatial predictive modeling. Each of these nine components is then reviewed, and guidelines for selecting and applying relevant components and developing accurate predictive models are provided. Finally, reproducible examples using <i>spm</i>, an R package, are provided to demonstrate how to select and develop predictive models using machine learning, geostatistics, and their hybrid methods according to predictive accuracy for spatial predictive modeling; reproducible examples are also provided to generate and visualize spatial predictions in environmental sciences.https://www.mdpi.com/2076-3417/9/10/2048spatial predictive modelspredictive accuracymodel assessmentvariable selectionfeature selectionmodel validationspatial predictionsreproducible research |
spellingShingle | Jin Li A Critical Review of Spatial Predictive Modeling Process in Environmental Sciences with Reproducible Examples in R Applied Sciences spatial predictive models predictive accuracy model assessment variable selection feature selection model validation spatial predictions reproducible research |
title | A Critical Review of Spatial Predictive Modeling Process in Environmental Sciences with Reproducible Examples in R |
title_full | A Critical Review of Spatial Predictive Modeling Process in Environmental Sciences with Reproducible Examples in R |
title_fullStr | A Critical Review of Spatial Predictive Modeling Process in Environmental Sciences with Reproducible Examples in R |
title_full_unstemmed | A Critical Review of Spatial Predictive Modeling Process in Environmental Sciences with Reproducible Examples in R |
title_short | A Critical Review of Spatial Predictive Modeling Process in Environmental Sciences with Reproducible Examples in R |
title_sort | critical review of spatial predictive modeling process in environmental sciences with reproducible examples in r |
topic | spatial predictive models predictive accuracy model assessment variable selection feature selection model validation spatial predictions reproducible research |
url | https://www.mdpi.com/2076-3417/9/10/2048 |
work_keys_str_mv | AT jinli acriticalreviewofspatialpredictivemodelingprocessinenvironmentalscienceswithreproducibleexamplesinr AT jinli criticalreviewofspatialpredictivemodelingprocessinenvironmentalscienceswithreproducibleexamplesinr |