Assessment of Soil Suitability Using Machine Learning in Arid and Semi-Arid Regions

被引:10
|
作者
Ismaili, Maryem [1 ,2 ]
Krimissa, Samira [1 ]
Namous, Mustapha [1 ]
Htitiou, Abdelaziz [1 ]
Abdelrahman, Kamal [3 ]
Fnais, Mohammed S. [3 ]
Lhissou, Rachid [4 ]
Eloudi, Hasna [5 ]
Faouzi, Elhousna [1 ]
Benabdelouahab, Tarik [2 ]
机构
[1] Sultan Moulay Slimane Univ, Dept Geol, Lab Data4Earth, Beni Mellal 23000, Morocco
[2] Natl Agron Res Inst, Rabat 10000, Morocco
[3] King Saud Univ, Coll Sci, Dept Geol & Geophys, POB 2455, Riyadh 11451, Saudi Arabia
[4] INRS, Ctr ETE, 490 Rue Couronne, Quebec City, PQ GIK 9A9, Canada
[5] Ibn Zohr Univ, Dept Geol, Agadir 80000, Morocco
来源
AGRONOMY-BASEL | 2023年 / 13卷 / 01期
关键词
precision agriculture; sentinel-2; random forest; XgbTree; digital soil mapping; remote sensing; agricultural management; MODIS TIME-SERIES; CLASSIFICATION; SALINITY; EROSION; SYSTEMS;
D O I
10.3390/agronomy13010165
中图分类号
S3 [农学(农艺学)];
学科分类号
0901 ;
摘要
Increasing agricultural production is a major concern that aims to increase income, reduce hunger, and improve other measures of well-being. Recently, the prediction of soil-suitability has become a primary topic of rising concern among academics, policymakers, and socio-economic analysts to assess dynamics of the agricultural production. This work aims to use physico-chemical and remotely sensed phenological parameters to produce soil-suitability maps (SSM) based on Machine Learning (ML) Algorithms in a semi-arid and arid region. Towards this goal an inventory of 238 suitability points has been carried out in addition to14 physico-chemical and 4 phenological parameters that have been used as inputs of machine-learning approaches which are five MLA prediction, namely RF, XgbTree, ANN, KNN and SVM. The results showed that phenological parameters were found to be the most influential in soil-suitability prediction. The validation of the Receiver Operating Characteristics (ROC) curve approach indicates an area under the curve and an AUC of more than 0.82 for all models. The best results were obtained using the XgbTree with an AUC = 0.97 in comparison to other MLA. Our findings demonstrate an excellent ability for ML models to predict the soil-suitability using physico-chemical and phenological parameters. The approach developed to map the soil-suitability is a valuable tool for sustainable agricultural development, and it can play an effective role in ensuring food security and conducting a land agriculture assessment.
引用
收藏
页数:16
相关论文
共 50 条
  • [1] Soil degradation and restoration in arid and semi-arid regions
    Wang, Kaibo
    Li, Jianping
    Zhou, Zhengchao
    Zhang, Xunchang John
    [J]. FRONTIERS IN ENVIRONMENTAL SCIENCE, 2023, 11
  • [2] Reference evapotranspiration estimation using machine learning approaches for arid and semi-arid regions of India
    Heramb, Pangam
    Rao, K. V.
    Subeesh, A.
    Singh, R. K.
    Rajwade, Yogesh A.
    Singh, Karan
    Kumar, Manoj
    Rawat, Shashi
    [J]. CLIMATE RESEARCH, 2023, 91 : 97 - 120
  • [3] Prediction of evaporation in arid and semi-arid regions: a comparative study using different machine learning models
    Yaseen, Zaher Mundher
    Al-Juboori, Anas Mahmood
    Beyaztas, Ufuk
    Al-Ansari, Nadhir
    Chau, Kwok-Wing
    Qi, Chongchong
    Ali, Mumtaz
    Salih, Sinan Q.
    Shahid, Shamsuddin
    [J]. ENGINEERING APPLICATIONS OF COMPUTATIONAL FLUID MECHANICS, 2020, 14 (01) : 70 - 89
  • [4] Mapping of Cornfield Soil Salinity in Arid and Semi-Arid Regions
    Smanov, Zhassulan Maratuly
    Laiskhanov, Shakhislam Uzakbaevich
    Poshanov, Maksat Nurbaiuly
    Abikbayev, Yerzhan Rakhimkeldievich
    Duisekov, Saken Nurzhanuly
    Tulegenov, Yerdaulet Askarbekovich
    [J]. JOURNAL OF ECOLOGICAL ENGINEERING, 2023, 24 (01): : 146 - 158
  • [5] Adaptive assessment of small ruminants in arid and semi-arid regions
    Gurgel Morais Leite, Jacinara Hody
    Evangelista Facanha, Debora Andrea
    Delgado Bermejo, Juan Vicente
    Guilhermino, Magda Maria
    Bermejo, Luis Alberto
    [J]. SMALL RUMINANT RESEARCH, 2021, 203
  • [6] Monitoring changes in soil organic carbon using satellite-based variables and machine learning algorithms in arid and semi-arid regions
    Hosseinpour-Zarnaq, Mohammad
    Moshiri, Farhad
    Jamshidi, Mohammad
    Taghizadeh-Mehrjardi, Ruhollah
    Tehrani, Mohammad Mehdi
    Ebrahimi Meymand, Fatemeh
    [J]. ENVIRONMENTAL EARTH SCIENCES, 2024, 83 (20)
  • [7] SOIL-MANAGEMENT FOR SEMI-ARID REGIONS
    LARSON, WE
    SWAN, JB
    SHAFFER, MJ
    [J]. AGRICULTURAL WATER MANAGEMENT, 1983, 7 (1-3) : 89 - 114
  • [8] A Contribution to Soil Fertility Assessment for Arid and Semi-Arid Lands
    Husein, Hussam Hag
    Lucke, Bernhard
    Baeumler, Rupert
    Sahwan, Wahib
    [J]. SOIL SYSTEMS, 2021, 5 (03)
  • [9] Assessment of soil CO2 and NO fluxes in a semi-arid region using machine learning approaches
    Mirzaei, Morad
    Caballero-Calvo, Andres
    Anari, Manouchehr Gorji
    -Pines, Eugenio Diaz
    Saronjic, Nermina
    Mohammed, Safwan
    Szabo, Szilard
    Mousavi, Seyed Mohammad Nasir
    [J]. JOURNAL OF ARID ENVIRONMENTS, 2023, 211
  • [10] Assessment of reptile response to habitat degradation in arid and semi-arid regions
    Elbahi, Abderrafea
    Lawton, Colin
    Oubrou, Widade
    El Bekkay, Mohammed
    Hermas, Jamila
    Dugon, Michel
    [J]. GLOBAL ECOLOGY AND CONSERVATION, 2023, 45