Machine learning performance for predicting soil salinity using different combinations of geomorphometric covariates

Divan Vermeulen, Adriaan Van Niekerk

    Research output: Contribution to journalArticle

    • 3 Citations

    Abstract

    Conventional methods of monitoring salt accumulation in irrigation schemes require regular field visits to collect soil samples for laboratory analysis. Identifying areas prone to salt accumulation by means of geomorphometry (i.e. terrain analyses using digital elevation models (DEMs)) can potentially save time and costs. This study evaluated the extent to which DEM derivatives and machine learning (ML) algorithms (k-nearest neighbour, support vector machine, decision tree (DT) and random forest) can be used for predicting the location and extent of salt-affected areas within the Vaalharts and Breede River irrigation schemes of South Africa. In accordance with local management policies, salt-affected areas were defined as regions with soil electrical conductivity (EC) values > 4 dS/m. Two DEMs, namely the one-arch second Shuttle Radar Topography Mission (SRTM) DEM and a photogrammetrically-extracted digital surface model (DSM), were used for deriving the derivatives. Wetness indices as well as hydrological and morphometric terrain analysis techniques were used to generate predictive variables. For comparative purposes, the predictive variables were also used as input to regression modelling and kriging with external drift (KED). Thresholds were applied to the regression models and KED results to obtain a binary classification. EC values based on in situ soil samples were used for model development, classifier training and accuracy assessment. The results show that KED achieved the highest overall accuracy (OA) in Vaalharts (79.6%), whereas KED and ML (DT) showed the most promise in the Breede River (75%). The findings suggest that the use of elevation data and its derivatives as input to geostatistics and ML holds much potential for monitoring salt accumulation in irrigated areas, particularly for simulating sub-surface conditions. More work is needed to investigate the potential of using ML and DEM-derivatives, along with other geospatial datasets such as satellite imagery (that have been shown to be effective for monitoring surface conditions), for the operational modelling of salt accumulation in large irrigation schemes.

    LanguageEnglish
    Pages1-12
    Number of pages12
    JournalGeoderma
    Volume299
    DOIs
    StatePublished - 1 Aug 2017

    Fingerprint

    artificial intelligence
    soil salinity
    digital elevation models
    digital elevation model
    kriging
    salt
    salts
    irrigation management
    irrigation
    electrical conductivity
    monitoring
    soil sampling
    Shuttle Radar Topography Mission
    rivers
    geostatistics
    accuracy assessment
    soil
    radar
    spatial data
    arch

    Cite this

    @article{5db42c0cab274647a98437cd54e75181,
    title = "Machine learning performance for predicting soil salinity using different combinations of geomorphometric covariates",
    abstract = "Conventional methods of monitoring salt accumulation in irrigation schemes require regular field visits to collect soil samples for laboratory analysis. Identifying areas prone to salt accumulation by means of geomorphometry (i.e. terrain analyses using digital elevation models (DEMs)) can potentially save time and costs. This study evaluated the extent to which DEM derivatives and machine learning (ML) algorithms (k-nearest neighbour, support vector machine, decision tree (DT) and random forest) can be used for predicting the location and extent of salt-affected areas within the Vaalharts and Breede River irrigation schemes of South Africa. In accordance with local management policies, salt-affected areas were defined as regions with soil electrical conductivity (EC) values > 4 dS/m. Two DEMs, namely the one-arch second Shuttle Radar Topography Mission (SRTM) DEM and a photogrammetrically-extracted digital surface model (DSM), were used for deriving the derivatives. Wetness indices as well as hydrological and morphometric terrain analysis techniques were used to generate predictive variables. For comparative purposes, the predictive variables were also used as input to regression modelling and kriging with external drift (KED). Thresholds were applied to the regression models and KED results to obtain a binary classification. EC values based on in situ soil samples were used for model development, classifier training and accuracy assessment. The results show that KED achieved the highest overall accuracy (OA) in Vaalharts (79.6{\%}), whereas KED and ML (DT) showed the most promise in the Breede River (75{\%}). The findings suggest that the use of elevation data and its derivatives as input to geostatistics and ML holds much potential for monitoring salt accumulation in irrigated areas, particularly for simulating sub-surface conditions. More work is needed to investigate the potential of using ML and DEM-derivatives, along with other geospatial datasets such as satellite imagery (that have been shown to be effective for monitoring surface conditions), for the operational modelling of salt accumulation in large irrigation schemes.",
    keywords = "Digital terrain analysis, Geomorphometry, Geostatistics, Hydrology, Machine learning, Salinity",
    author = "Divan Vermeulen and {Van Niekerk}, Adriaan",
    year = "2017",
    month = "8",
    day = "1",
    doi = "10.1016/j.geoderma.2017.03.013",
    language = "English",
    volume = "299",
    pages = "1--12",
    journal = "Geoderma",
    issn = "0016-7061",
    publisher = "Elsevier",

    }

    Machine learning performance for predicting soil salinity using different combinations of geomorphometric covariates. / Vermeulen, Divan; Van Niekerk, Adriaan.

    In: Geoderma, Vol. 299, 01.08.2017, p. 1-12.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Machine learning performance for predicting soil salinity using different combinations of geomorphometric covariates

    AU - Vermeulen,Divan

    AU - Van Niekerk,Adriaan

    PY - 2017/8/1

    Y1 - 2017/8/1

    N2 - Conventional methods of monitoring salt accumulation in irrigation schemes require regular field visits to collect soil samples for laboratory analysis. Identifying areas prone to salt accumulation by means of geomorphometry (i.e. terrain analyses using digital elevation models (DEMs)) can potentially save time and costs. This study evaluated the extent to which DEM derivatives and machine learning (ML) algorithms (k-nearest neighbour, support vector machine, decision tree (DT) and random forest) can be used for predicting the location and extent of salt-affected areas within the Vaalharts and Breede River irrigation schemes of South Africa. In accordance with local management policies, salt-affected areas were defined as regions with soil electrical conductivity (EC) values > 4 dS/m. Two DEMs, namely the one-arch second Shuttle Radar Topography Mission (SRTM) DEM and a photogrammetrically-extracted digital surface model (DSM), were used for deriving the derivatives. Wetness indices as well as hydrological and morphometric terrain analysis techniques were used to generate predictive variables. For comparative purposes, the predictive variables were also used as input to regression modelling and kriging with external drift (KED). Thresholds were applied to the regression models and KED results to obtain a binary classification. EC values based on in situ soil samples were used for model development, classifier training and accuracy assessment. The results show that KED achieved the highest overall accuracy (OA) in Vaalharts (79.6%), whereas KED and ML (DT) showed the most promise in the Breede River (75%). The findings suggest that the use of elevation data and its derivatives as input to geostatistics and ML holds much potential for monitoring salt accumulation in irrigated areas, particularly for simulating sub-surface conditions. More work is needed to investigate the potential of using ML and DEM-derivatives, along with other geospatial datasets such as satellite imagery (that have been shown to be effective for monitoring surface conditions), for the operational modelling of salt accumulation in large irrigation schemes.

    AB - Conventional methods of monitoring salt accumulation in irrigation schemes require regular field visits to collect soil samples for laboratory analysis. Identifying areas prone to salt accumulation by means of geomorphometry (i.e. terrain analyses using digital elevation models (DEMs)) can potentially save time and costs. This study evaluated the extent to which DEM derivatives and machine learning (ML) algorithms (k-nearest neighbour, support vector machine, decision tree (DT) and random forest) can be used for predicting the location and extent of salt-affected areas within the Vaalharts and Breede River irrigation schemes of South Africa. In accordance with local management policies, salt-affected areas were defined as regions with soil electrical conductivity (EC) values > 4 dS/m. Two DEMs, namely the one-arch second Shuttle Radar Topography Mission (SRTM) DEM and a photogrammetrically-extracted digital surface model (DSM), were used for deriving the derivatives. Wetness indices as well as hydrological and morphometric terrain analysis techniques were used to generate predictive variables. For comparative purposes, the predictive variables were also used as input to regression modelling and kriging with external drift (KED). Thresholds were applied to the regression models and KED results to obtain a binary classification. EC values based on in situ soil samples were used for model development, classifier training and accuracy assessment. The results show that KED achieved the highest overall accuracy (OA) in Vaalharts (79.6%), whereas KED and ML (DT) showed the most promise in the Breede River (75%). The findings suggest that the use of elevation data and its derivatives as input to geostatistics and ML holds much potential for monitoring salt accumulation in irrigated areas, particularly for simulating sub-surface conditions. More work is needed to investigate the potential of using ML and DEM-derivatives, along with other geospatial datasets such as satellite imagery (that have been shown to be effective for monitoring surface conditions), for the operational modelling of salt accumulation in large irrigation schemes.

    KW - Digital terrain analysis

    KW - Geomorphometry

    KW - Geostatistics

    KW - Hydrology

    KW - Machine learning

    KW - Salinity

    UR - http://www.scopus.com/inward/record.url?scp=85016409027&partnerID=8YFLogxK

    U2 - 10.1016/j.geoderma.2017.03.013

    DO - 10.1016/j.geoderma.2017.03.013

    M3 - Article

    VL - 299

    SP - 1

    EP - 12

    JO - Geoderma

    T2 - Geoderma

    JF - Geoderma

    SN - 0016-7061

    ER -