2016
DOI: 10.3390/agriculture6040052
|View full text |Cite
|
Sign up to set email alerts
|

Feature Selection as a Time and Cost-Saving Approach for Land Suitability Classification (Case Study of Shavur Plain, Iran)

Abstract: Land suitability classification is important in planning and managing sustainable land use. Most approaches to land suitability analysis combine a large number of land and soil parameters, and are time-consuming and costly. In this study, a potentially useful technique (combined feature selection and fuzzy-AHP method) to increase the efficiency of land suitability analysis was presented. To this end, three different feature selection algorithms-random search, best search and genetic methods-were used to determ… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
7
0

Year Published

2017
2017
2021
2021

Publication Types

Select...
9

Relationship

0
9

Authors

Journals

citations
Cited by 17 publications
(7 citation statements)
references
References 37 publications
0
7
0
Order By: Relevance
“…While the common approach is to use a 2 class (suitable/unsuitable) approach for modelling crop suitability [44][45][46][47], we propose a method that models four suitability classes (optimal, moderate, marginal and limited) as a 2 class system may over-estimate climate impacts by not scaling the suitability. Scaled four-class (high, moderate, marginal and unsuitable) suitability models are an alternative for determining suitability classes of agricultural crops from machine learning algorithms [31,[48][49][50][51]. To model the four suitability classes of the four crops, we applied the eXtreme Gradient Boosting (XGBoost) machine learning approach to the variables.…”
Section: Modelling Approachmentioning
confidence: 99%
“…While the common approach is to use a 2 class (suitable/unsuitable) approach for modelling crop suitability [44][45][46][47], we propose a method that models four suitability classes (optimal, moderate, marginal and limited) as a 2 class system may over-estimate climate impacts by not scaling the suitability. Scaled four-class (high, moderate, marginal and unsuitable) suitability models are an alternative for determining suitability classes of agricultural crops from machine learning algorithms [31,[48][49][50][51]. To model the four suitability classes of the four crops, we applied the eXtreme Gradient Boosting (XGBoost) machine learning approach to the variables.…”
Section: Modelling Approachmentioning
confidence: 99%
“…Land suitability assessment plays an important role in planning and managing sustainable land use [13]. It provides useful information and helps in optimizing agricultural land use [14].…”
Section: Introductionmentioning
confidence: 99%
“…They found that soil texture, wetness, salinity and alkalinity were the most effective parameters for determining land suitability classification for the cultivation of barely in the Shavur Plain, doi: 10.17700/jai.2017.8.3.390 24 Kennedy Mutange Senagi, Nicolas Jouandeau, Peter Kamoni: Using Parallel Random Forest Classifier in Predicting Land Suitability for Crop Production southwest Iran. The report showed that soil salinity and alkalinity, soil wetness, CaCO3, gypsum, pH, soil texture, soil depth and topography were the most important soil properties to consider for cultivating barley in the study area (Hamzeh et al 2016). Mokarram et al (2015) used AI and ML to automate the land suitability classification for growing wheat.…”
Section: Related Workmentioning
confidence: 97%
“…Land suitability classification using a large number of parameters is time consuming and costly. With this research problem Hamzeh et al (2016) presented a combination of feature selection (best search, random search and genetic search methods) and fuzzy-analytical hierarchical process (AHP) methods to improve selection of important features from a large number of parameters. On feature selection, random search performed slightly better than genetic search methods and best search.…”
Section: Related Workmentioning
confidence: 99%