Characterization of portuguese sown rainfed grasslands using remote sensing and machine learning View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2022-07-27

AUTHORS

Tiago G. Morais, Marjan Jongen, Camila Tufik, Nuno R. Rodrigues, Ivo Gama, David Fangueiro, João Serrano, Susana Vieira, Tiago Domingos, Ricardo F.M. Teixeira

ABSTRACT

Grasslands are crucial ecosystems that support and provide a diverse number of ecosystem services. Sown biodiverse pastures rich in legumes (SBP) were developed with the main goal of increasing grassland production while minimizing fertilizers inputs. In this paper, the main properties of SBP in Portugal were estimated using remote sensing and machine learning in six different farms and two production years (spring 2018 and 2019). Four pasture characteristics were considered: aboveground standing biomass, fraction of legumes, plant nitrogen (N) content and plant phosphorus (P) content. Remote sensing data were obtained from Sentinel-2. The spectral bands combined with 5 vegetation indices and 9 covariates were used. Multiple linear regression, LASSO, Ridge, random forests, XGBoost and LightGBM regression models were used. Two cross-validation approaches were used: (1) a random approach with random selection of the folds (RN-CV), and (2) a structured approach where each fold is a unique combination of farm and year, which is subsequently used to assess the performance of the model obtained with the 8 other folds (LLYO-CV). Results showed that the random forest method had the best estimation accuracy for all pasture characteristics. Regarding cross-validation approaches, the algorithms with RN-CV have higher estimation accuracy for all pasture characteristics (on average about 10% lower RMSE and an R2 85% higher), as compared to the algorithms with LLYO-CV. However, LLYO-CV should avoid overfitting and improve generalization of the models because in each fold the model is tested in a farm and year that was not used for training. The RMSE for all variables were significantly low, especially in RN-CV. Plant P is the variable where the choice of CV approach has the least influence (RMSE of test set with RN-CV: 0.71 g P kg− 1; LLYO-CV: 0.72 g P kg− 1). Standing biomass is the variable with the highest difference between CV approaches (RN-CV: 722 kg ha− 1; LLYO-CV: 825 kg ha− 1). The RMSE, of legumes and plant N were moderately affected by the CV approach (legume RN-CV: 0.11; LLYO-CV: 0.12 – plant N RN-CV: 3.96 g N kg− 1; LLYO-CV: 3.99 g N kg− 1). The algorithms developed here were applied for entire parcels in the two farms with the most different climate conditions as demonstration of their potential future use for precision farming. More... »

PAGES

1-26

References to SciGraph publications

  • 2020-09-16. Array programming with NumPy in NATURE
  • 2018-07-24. Combined use of in situ hyperspectral vegetation indices for estimating pasture biomass at peak productive period for harvest decision in PRECISION AGRICULTURE
  • 2015-10-30. Monitoring of soil organic carbon over 10 years in a Mediterranean silvo-pastoral system: potential evaluation for differential management in PRECISION AGRICULTURE
  • 2021-06-17. Suitability of satellite remote sensing data for yield estimation in northeast Germany in PRECISION AGRICULTURE
  • 2011-11-13. In-field hyperspectral proximal sensing for estimating quality parameters of mixed pasture in PRECISION AGRICULTURE
  • 2021-04-21. Automation in Agriculture by Machine and Deep Learning Techniques: A Review of Recent Developments in PRECISION AGRICULTURE
  • 2012-07-31. The application of small unmanned aerial systems for precision agriculture: a review in PRECISION AGRICULTURE
  • 2011-05-05. Effects of grazing on seasonal variation of aboveground biomass quality in calcareous grasslands in PLANT ECOLOGY
  • 2015-01-20. A review of radar remote sensing for biomass estimation in INTERNATIONAL JOURNAL OF ENVIRONMENTAL SCIENCE AND TECHNOLOGY
  • 2022-03-05. A survey of few-shot learning in smart agriculture: developments, applications, and challenges in PLANT METHODS
  • 2006-02. Principles of Development of a Mass Balance N Cycle Model for Temperate Grasslands: An Irish Case Study in NUTRIENT CYCLING IN AGROECOSYSTEMS
  • 2020-01-23. Performance of chlorophyll prediction indices for Eragrostis tef at Sentinel-2 MSI and Landsat-8 OLI spectral resolutions in PRECISION AGRICULTURE
  • 2018-02-19. Increasing importance of precipitation variability on global livestock grazing lands in NATURE CLIMATE CHANGE
  • 2013-06-01. Estimating aboveground biomass in Mu Us Sandy Land using Landsat spectral derived vegetation indices over the past 30 years in JOURNAL OF ARID LAND
  • 2019-05-02. Remotely sensed indicators and open-access biodiversity data to assess bird diversity patterns in Mediterranean rural landscapes in SCIENTIFIC REPORTS
  • 2021-04-12. Sowing enriched pastures for extensive livestock enhances the abundance of birds and arthropods in Mediterranean grasslands in EUROPEAN JOURNAL OF WILDLIFE RESEARCH
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s11119-022-09937-9

    DOI

    http://dx.doi.org/10.1007/s11119-022-09937-9

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1149794624


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/07", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Agricultural and Veterinary Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0703", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Crop and Pasture Production", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "MARETEC \u2013 Marine, Environment and Technology Centre, LARSyS, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Av. Rovisco Pais, 1, 1049-001, Lisboa, Portugal", 
              "id": "http://www.grid.ac/institutes/grid.9983.b", 
              "name": [
                "MARETEC \u2013 Marine, Environment and Technology Centre, LARSyS, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Av. Rovisco Pais, 1, 1049-001, Lisboa, Portugal"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Morais", 
            "givenName": "Tiago G.", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Centro de Estudos Florestais (CEF), Instituto Superior de Agronomia, Universidade de Lisboa, Tapada da Ajuda, 1349-017, Lisboa, Portugal", 
              "id": "http://www.grid.ac/institutes/grid.9983.b", 
              "name": [
                "MARETEC \u2013 Marine, Environment and Technology Centre, LARSyS, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Av. Rovisco Pais, 1, 1049-001, Lisboa, Portugal", 
                "Centro de Estudos Florestais (CEF), Instituto Superior de Agronomia, Universidade de Lisboa, Tapada da Ajuda, 1349-017, Lisboa, Portugal"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Jongen", 
            "givenName": "Marjan", 
            "id": "sg:person.01231224052.28", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01231224052.28"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Linking Landscape, Environment, Agriculture and Food (LEAF), Instituto Superior de Agronomia, Universidade de Lisboa, Tapada da Ajuda, 1349-017, Lisboa, Portugal", 
              "id": "http://www.grid.ac/institutes/grid.9983.b", 
              "name": [
                "Linking Landscape, Environment, Agriculture and Food (LEAF), Instituto Superior de Agronomia, Universidade de Lisboa, Tapada da Ajuda, 1349-017, Lisboa, Portugal"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Tufik", 
            "givenName": "Camila", 
            "id": "sg:person.015750134410.90", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015750134410.90"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Terraprima \u2013 Servi\u00e7os Ambientais, Sociedade Unipessoal, Lda, 2135-199, Samora Correia, Portugal", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Terraprima \u2013 Servi\u00e7os Ambientais, Sociedade Unipessoal, Lda, 2135-199, Samora Correia, Portugal"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Rodrigues", 
            "givenName": "Nuno R.", 
            "id": "sg:person.011504076050.36", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011504076050.36"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Terraprima \u2013 Servi\u00e7os Ambientais, Sociedade Unipessoal, Lda, 2135-199, Samora Correia, Portugal", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Terraprima \u2013 Servi\u00e7os Ambientais, Sociedade Unipessoal, Lda, 2135-199, Samora Correia, Portugal"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Gama", 
            "givenName": "Ivo", 
            "id": "sg:person.01344743243.18", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01344743243.18"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Linking Landscape, Environment, Agriculture and Food (LEAF), Instituto Superior de Agronomia, Universidade de Lisboa, Tapada da Ajuda, 1349-017, Lisboa, Portugal", 
              "id": "http://www.grid.ac/institutes/grid.9983.b", 
              "name": [
                "Linking Landscape, Environment, Agriculture and Food (LEAF), Instituto Superior de Agronomia, Universidade de Lisboa, Tapada da Ajuda, 1349-017, Lisboa, Portugal"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Fangueiro", 
            "givenName": "David", 
            "id": "sg:person.0661045224.15", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0661045224.15"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Mediterranean Institute for Agriculture, Environment and Development (MED), Universidade de \u00c9vora, P.O. Box 94, 7002-554, \u00c9vora, Portugal", 
              "id": "http://www.grid.ac/institutes/grid.8389.a", 
              "name": [
                "Mediterranean Institute for Agriculture, Environment and Development (MED), Universidade de \u00c9vora, P.O. Box 94, 7002-554, \u00c9vora, Portugal"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Serrano", 
            "givenName": "Jo\u00e3o", 
            "id": "sg:person.012560552411.84", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012560552411.84"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "IDMEC - Mechanical Engineering Institute, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Av. Rovisco Pais, 1, 1049-001, Lisbon, Portugal", 
              "id": "http://www.grid.ac/institutes/grid.9983.b", 
              "name": [
                "IDMEC - Mechanical Engineering Institute, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Av. Rovisco Pais, 1, 1049-001, Lisbon, Portugal"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Vieira", 
            "givenName": "Susana", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "MARETEC \u2013 Marine, Environment and Technology Centre, LARSyS, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Av. Rovisco Pais, 1, 1049-001, Lisboa, Portugal", 
              "id": "http://www.grid.ac/institutes/grid.9983.b", 
              "name": [
                "MARETEC \u2013 Marine, Environment and Technology Centre, LARSyS, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Av. Rovisco Pais, 1, 1049-001, Lisboa, Portugal"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Domingos", 
            "givenName": "Tiago", 
            "id": "sg:person.01354645302.63", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01354645302.63"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "MARETEC \u2013 Marine, Environment and Technology Centre, LARSyS, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Av. Rovisco Pais, 1, 1049-001, Lisboa, Portugal", 
              "id": "http://www.grid.ac/institutes/grid.9983.b", 
              "name": [
                "MARETEC \u2013 Marine, Environment and Technology Centre, LARSyS, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Av. Rovisco Pais, 1, 1049-001, Lisboa, Portugal"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Teixeira", 
            "givenName": "Ricardo F.M.", 
            "id": "sg:person.0637362650.44", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0637362650.44"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/s40333-013-0180-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1009845820", 
              "https://doi.org/10.1007/s40333-013-0180-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s13762-015-0750-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1036376145", 
              "https://doi.org/10.1007/s13762-015-0750-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11119-020-09708-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1124280830", 
              "https://doi.org/10.1007/s11119-020-09708-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s10705-005-5769-z", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1005778597", 
              "https://doi.org/10.1007/s10705-005-5769-z"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s10344-021-01486-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1137145014", 
              "https://doi.org/10.1007/s10344-021-01486-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s13007-022-00866-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1146074958", 
              "https://doi.org/10.1186/s13007-022-00866-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11258-011-9931-1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024905558", 
              "https://doi.org/10.1007/s11258-011-9931-1"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11119-021-09806-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1137371122", 
              "https://doi.org/10.1007/s11119-021-09806-x"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11119-012-9274-5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1020655667", 
              "https://doi.org/10.1007/s11119-012-9274-5"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11119-011-9251-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1013175984", 
              "https://doi.org/10.1007/s11119-011-9251-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11119-018-9592-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1105803503", 
              "https://doi.org/10.1007/s11119-018-9592-3"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41586-020-2649-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1130863323", 
              "https://doi.org/10.1038/s41586-020-2649-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11119-015-9419-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1036395932", 
              "https://doi.org/10.1007/s11119-015-9419-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11119-021-09827-6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1138950866", 
              "https://doi.org/10.1007/s11119-021-09827-6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41598-019-43330-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1113875044", 
              "https://doi.org/10.1038/s41598-019-43330-3"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41558-018-0081-5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1101086651", 
              "https://doi.org/10.1038/s41558-018-0081-5"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2022-07-27", 
        "datePublishedReg": "2022-07-27", 
        "description": "Grasslands are crucial ecosystems that support and provide a diverse number of ecosystem services. Sown biodiverse pastures rich in legumes (SBP) were developed with the main goal of increasing grassland production while minimizing fertilizers inputs. In this paper, the main properties of SBP in Portugal were estimated using remote sensing and machine learning in six different farms and two production years (spring 2018 and 2019). Four pasture characteristics were considered: aboveground standing biomass, fraction of legumes, plant nitrogen (N) content and plant phosphorus (P) content. Remote sensing data were obtained from Sentinel-2. The spectral bands combined with 5 vegetation indices and 9 covariates were used. Multiple linear regression, LASSO, Ridge, random forests, XGBoost and LightGBM regression models were used. Two cross-validation approaches were used: (1) a random approach with random selection of the folds (RN-CV), and (2) a structured approach where each fold is a unique combination of farm and year, which is subsequently used to assess the performance of the model obtained with the 8 other folds (LLYO-CV). Results showed that the random forest method had the best estimation accuracy for all pasture characteristics. Regarding cross-validation approaches, the algorithms with RN-CV have higher estimation accuracy for all pasture characteristics (on average about 10% lower RMSE and an R2 85% higher), as compared to the algorithms with LLYO-CV. However, LLYO-CV should avoid overfitting and improve generalization of the models because in each fold the model is tested in a farm and year that was not used for training. The RMSE for all variables were significantly low, especially in RN-CV. Plant P is the variable where the choice of CV approach has the least influence (RMSE of test set with RN-CV: 0.71\u00a0g P kg\u2212\u20091; LLYO-CV: 0.72\u00a0g P kg\u2212\u20091). Standing biomass is the variable with the highest difference between CV approaches (RN-CV: 722\u00a0kg ha\u2212\u20091; LLYO-CV: 825\u00a0kg ha\u2212\u20091). The RMSE, of legumes and plant N were moderately affected by the CV approach (legume RN-CV: 0.11; LLYO-CV: 0.12 \u2013 plant N RN-CV: 3.96\u00a0g N kg\u2212\u20091; LLYO-CV: 3.99\u00a0g N kg\u2212\u20091). The algorithms developed here were applied for entire parcels in the two farms with the most different climate conditions as demonstration of their potential future use for precision farming.", 
        "genre": "article", 
        "id": "sg:pub.10.1007/s11119-022-09937-9", 
        "isAccessibleForFree": false, 
        "isFundedItemOf": [
          {
            "id": "sg:grant.9757102", 
            "type": "MonetaryGrant"
          }, 
          {
            "id": "sg:grant.9762520", 
            "type": "MonetaryGrant"
          }, 
          {
            "id": "sg:grant.9763148", 
            "type": "MonetaryGrant"
          }, 
          {
            "id": "sg:grant.9568864", 
            "type": "MonetaryGrant"
          }, 
          {
            "id": "sg:grant.9760900", 
            "type": "MonetaryGrant"
          }, 
          {
            "id": "sg:grant.9567930", 
            "type": "MonetaryGrant"
          }, 
          {
            "id": "sg:grant.9597640", 
            "type": "MonetaryGrant"
          }
        ], 
        "isPartOf": [
          {
            "id": "sg:journal.1135929", 
            "issn": [
              "1385-2256", 
              "1573-1618"
            ], 
            "name": "Precision Agriculture", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }
        ], 
        "keywords": [
          "remote sensing", 
          "pasture characteristics", 
          "plant phosphorus content", 
          "plant nitrogen content", 
          "crucial ecosystems", 
          "ecosystem services", 
          "grassland production", 
          "standing biomass", 
          "biodiverse pastures", 
          "fertilizer inputs", 
          "plant P", 
          "vegetation index", 
          "entire parcels", 
          "plant N", 
          "Sentinel-2", 
          "climate conditions", 
          "phosphorus content", 
          "precision farming", 
          "nitrogen content", 
          "grasslands", 
          "different climate conditions", 
          "legumes", 
          "random forest method", 
          "biomass", 
          "cross-validation approach", 
          "farms", 
          "spectral bands", 
          "CV approach", 
          "multiple linear regression", 
          "forest method", 
          "ecosystems", 
          "highest difference", 
          "forest", 
          "production year", 
          "pasture", 
          "random approach", 
          "random forest", 
          "different farms", 
          "RMSE", 
          "farming", 
          "sensing", 
          "unique combination", 
          "parcels", 
          "diverse number", 
          "least influence", 
          "future use", 
          "content", 
          "variables", 
          "linear regression", 
          "potential future use", 
          "Portugal", 
          "input", 
          "random selection", 
          "years", 
          "structured approach", 
          "main goal", 
          "index", 
          "characteristics", 
          "ridge", 
          "regression models", 
          "approach", 
          "estimation accuracy", 
          "production", 
          "better estimation accuracy", 
          "selection", 
          "fraction", 
          "services", 
          "influence", 
          "model", 
          "use", 
          "covariates", 
          "high estimation accuracy", 
          "goal", 
          "conditions", 
          "machine learning", 
          "differences", 
          "data", 
          "combination", 
          "results", 
          "algorithm", 
          "regression", 
          "number", 
          "LASSO", 
          "properties", 
          "accuracy", 
          "XGBoost", 
          "machine", 
          "main properties", 
          "method", 
          "learning", 
          "choice", 
          "folds", 
          "generalization", 
          "performance", 
          "characterization", 
          "paper", 
          "training", 
          "band", 
          "demonstration", 
          "SBP"
        ], 
        "name": "Characterization of portuguese sown rainfed grasslands using remote sensing and machine learning", 
        "pagination": "1-26", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1149794624"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s11119-022-09937-9"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s11119-022-09937-9", 
          "https://app.dimensions.ai/details/publication/pub.1149794624"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-10-01T06:50", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20221001/entities/gbq_results/article/article_933.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1007/s11119-022-09937-9"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/s11119-022-09937-9'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s11119-022-09937-9'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s11119-022-09937-9'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s11119-022-09937-9'


     

    This table displays all metadata directly associated to this object as RDF triples.

    302 TRIPLES      21 PREDICATES      138 URIs      114 LITERALS      4 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s11119-022-09937-9 schema:about anzsrc-for:07
    2 anzsrc-for:0703
    3 schema:author N831fc26f36b8432a9fe5863748e88f02
    4 schema:citation sg:pub.10.1007/s10344-021-01486-2
    5 sg:pub.10.1007/s10705-005-5769-z
    6 sg:pub.10.1007/s11119-011-9251-4
    7 sg:pub.10.1007/s11119-012-9274-5
    8 sg:pub.10.1007/s11119-015-9419-4
    9 sg:pub.10.1007/s11119-018-9592-3
    10 sg:pub.10.1007/s11119-020-09708-4
    11 sg:pub.10.1007/s11119-021-09806-x
    12 sg:pub.10.1007/s11119-021-09827-6
    13 sg:pub.10.1007/s11258-011-9931-1
    14 sg:pub.10.1007/s13762-015-0750-0
    15 sg:pub.10.1007/s40333-013-0180-0
    16 sg:pub.10.1038/s41558-018-0081-5
    17 sg:pub.10.1038/s41586-020-2649-2
    18 sg:pub.10.1038/s41598-019-43330-3
    19 sg:pub.10.1186/s13007-022-00866-2
    20 schema:datePublished 2022-07-27
    21 schema:datePublishedReg 2022-07-27
    22 schema:description Grasslands are crucial ecosystems that support and provide a diverse number of ecosystem services. Sown biodiverse pastures rich in legumes (SBP) were developed with the main goal of increasing grassland production while minimizing fertilizers inputs. In this paper, the main properties of SBP in Portugal were estimated using remote sensing and machine learning in six different farms and two production years (spring 2018 and 2019). Four pasture characteristics were considered: aboveground standing biomass, fraction of legumes, plant nitrogen (N) content and plant phosphorus (P) content. Remote sensing data were obtained from Sentinel-2. The spectral bands combined with 5 vegetation indices and 9 covariates were used. Multiple linear regression, LASSO, Ridge, random forests, XGBoost and LightGBM regression models were used. Two cross-validation approaches were used: (1) a random approach with random selection of the folds (RN-CV), and (2) a structured approach where each fold is a unique combination of farm and year, which is subsequently used to assess the performance of the model obtained with the 8 other folds (LLYO-CV). Results showed that the random forest method had the best estimation accuracy for all pasture characteristics. Regarding cross-validation approaches, the algorithms with RN-CV have higher estimation accuracy for all pasture characteristics (on average about 10% lower RMSE and an R2 85% higher), as compared to the algorithms with LLYO-CV. However, LLYO-CV should avoid overfitting and improve generalization of the models because in each fold the model is tested in a farm and year that was not used for training. The RMSE for all variables were significantly low, especially in RN-CV. Plant P is the variable where the choice of CV approach has the least influence (RMSE of test set with RN-CV: 0.71 g P kg− 1; LLYO-CV: 0.72 g P kg− 1). Standing biomass is the variable with the highest difference between CV approaches (RN-CV: 722 kg ha− 1; LLYO-CV: 825 kg ha− 1). The RMSE, of legumes and plant N were moderately affected by the CV approach (legume RN-CV: 0.11; LLYO-CV: 0.12 – plant N RN-CV: 3.96 g N kg− 1; LLYO-CV: 3.99 g N kg− 1). The algorithms developed here were applied for entire parcels in the two farms with the most different climate conditions as demonstration of their potential future use for precision farming.
    23 schema:genre article
    24 schema:isAccessibleForFree false
    25 schema:isPartOf sg:journal.1135929
    26 schema:keywords CV approach
    27 LASSO
    28 Portugal
    29 RMSE
    30 SBP
    31 Sentinel-2
    32 XGBoost
    33 accuracy
    34 algorithm
    35 approach
    36 band
    37 better estimation accuracy
    38 biodiverse pastures
    39 biomass
    40 characteristics
    41 characterization
    42 choice
    43 climate conditions
    44 combination
    45 conditions
    46 content
    47 covariates
    48 cross-validation approach
    49 crucial ecosystems
    50 data
    51 demonstration
    52 differences
    53 different climate conditions
    54 different farms
    55 diverse number
    56 ecosystem services
    57 ecosystems
    58 entire parcels
    59 estimation accuracy
    60 farming
    61 farms
    62 fertilizer inputs
    63 folds
    64 forest
    65 forest method
    66 fraction
    67 future use
    68 generalization
    69 goal
    70 grassland production
    71 grasslands
    72 high estimation accuracy
    73 highest difference
    74 index
    75 influence
    76 input
    77 learning
    78 least influence
    79 legumes
    80 linear regression
    81 machine
    82 machine learning
    83 main goal
    84 main properties
    85 method
    86 model
    87 multiple linear regression
    88 nitrogen content
    89 number
    90 paper
    91 parcels
    92 pasture
    93 pasture characteristics
    94 performance
    95 phosphorus content
    96 plant N
    97 plant P
    98 plant nitrogen content
    99 plant phosphorus content
    100 potential future use
    101 precision farming
    102 production
    103 production year
    104 properties
    105 random approach
    106 random forest
    107 random forest method
    108 random selection
    109 regression
    110 regression models
    111 remote sensing
    112 results
    113 ridge
    114 selection
    115 sensing
    116 services
    117 spectral bands
    118 standing biomass
    119 structured approach
    120 training
    121 unique combination
    122 use
    123 variables
    124 vegetation index
    125 years
    126 schema:name Characterization of portuguese sown rainfed grasslands using remote sensing and machine learning
    127 schema:pagination 1-26
    128 schema:productId N8d1d02dbf0f34fe59cb7e42477dc876a
    129 Neff99de036724842b0f0015105617141
    130 schema:sameAs https://app.dimensions.ai/details/publication/pub.1149794624
    131 https://doi.org/10.1007/s11119-022-09937-9
    132 schema:sdDatePublished 2022-10-01T06:50
    133 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    134 schema:sdPublisher N0677a5b9a45844c19343b78e239c9020
    135 schema:url https://doi.org/10.1007/s11119-022-09937-9
    136 sgo:license sg:explorer/license/
    137 sgo:sdDataset articles
    138 rdf:type schema:ScholarlyArticle
    139 N0677a5b9a45844c19343b78e239c9020 schema:name Springer Nature - SN SciGraph project
    140 rdf:type schema:Organization
    141 N11e490d3c53941b1b9c12bb066e7cfc5 rdf:first sg:person.011504076050.36
    142 rdf:rest N6e4a3d43c0034be5bae7f7474a4355e0
    143 N20fdf05317d34d6c9383f397b372e3b8 schema:affiliation grid-institutes:grid.9983.b
    144 schema:familyName Morais
    145 schema:givenName Tiago G.
    146 rdf:type schema:Person
    147 N26b21f8a37bc40669ed82bdee778b637 rdf:first N506c555b62d441cc8e7ac307dafaafa6
    148 rdf:rest N90594b490f074fe690c7a0d34f92cd1d
    149 N2e964d9dc4bb41b084c1cd4a95062cfc rdf:first sg:person.012560552411.84
    150 rdf:rest N26b21f8a37bc40669ed82bdee778b637
    151 N506c555b62d441cc8e7ac307dafaafa6 schema:affiliation grid-institutes:grid.9983.b
    152 schema:familyName Vieira
    153 schema:givenName Susana
    154 rdf:type schema:Person
    155 N5eda65eed02641009af6dcb7e7aca9ed rdf:first sg:person.0637362650.44
    156 rdf:rest rdf:nil
    157 N6e4a3d43c0034be5bae7f7474a4355e0 rdf:first sg:person.01344743243.18
    158 rdf:rest Nb016fef40fa847c3a75ea0779ac7fc09
    159 N775ed06872c747199fe03ac0427cc998 rdf:first sg:person.015750134410.90
    160 rdf:rest N11e490d3c53941b1b9c12bb066e7cfc5
    161 N7920782faee245ada7fadeb5c61bf50b rdf:first sg:person.01231224052.28
    162 rdf:rest N775ed06872c747199fe03ac0427cc998
    163 N831fc26f36b8432a9fe5863748e88f02 rdf:first N20fdf05317d34d6c9383f397b372e3b8
    164 rdf:rest N7920782faee245ada7fadeb5c61bf50b
    165 N8d1d02dbf0f34fe59cb7e42477dc876a schema:name dimensions_id
    166 schema:value pub.1149794624
    167 rdf:type schema:PropertyValue
    168 N90594b490f074fe690c7a0d34f92cd1d rdf:first sg:person.01354645302.63
    169 rdf:rest N5eda65eed02641009af6dcb7e7aca9ed
    170 Nb016fef40fa847c3a75ea0779ac7fc09 rdf:first sg:person.0661045224.15
    171 rdf:rest N2e964d9dc4bb41b084c1cd4a95062cfc
    172 Neff99de036724842b0f0015105617141 schema:name doi
    173 schema:value 10.1007/s11119-022-09937-9
    174 rdf:type schema:PropertyValue
    175 anzsrc-for:07 schema:inDefinedTermSet anzsrc-for:
    176 schema:name Agricultural and Veterinary Sciences
    177 rdf:type schema:DefinedTerm
    178 anzsrc-for:0703 schema:inDefinedTermSet anzsrc-for:
    179 schema:name Crop and Pasture Production
    180 rdf:type schema:DefinedTerm
    181 sg:grant.9567930 http://pending.schema.org/fundedItem sg:pub.10.1007/s11119-022-09937-9
    182 rdf:type schema:MonetaryGrant
    183 sg:grant.9568864 http://pending.schema.org/fundedItem sg:pub.10.1007/s11119-022-09937-9
    184 rdf:type schema:MonetaryGrant
    185 sg:grant.9597640 http://pending.schema.org/fundedItem sg:pub.10.1007/s11119-022-09937-9
    186 rdf:type schema:MonetaryGrant
    187 sg:grant.9757102 http://pending.schema.org/fundedItem sg:pub.10.1007/s11119-022-09937-9
    188 rdf:type schema:MonetaryGrant
    189 sg:grant.9760900 http://pending.schema.org/fundedItem sg:pub.10.1007/s11119-022-09937-9
    190 rdf:type schema:MonetaryGrant
    191 sg:grant.9762520 http://pending.schema.org/fundedItem sg:pub.10.1007/s11119-022-09937-9
    192 rdf:type schema:MonetaryGrant
    193 sg:grant.9763148 http://pending.schema.org/fundedItem sg:pub.10.1007/s11119-022-09937-9
    194 rdf:type schema:MonetaryGrant
    195 sg:journal.1135929 schema:issn 1385-2256
    196 1573-1618
    197 schema:name Precision Agriculture
    198 schema:publisher Springer Nature
    199 rdf:type schema:Periodical
    200 sg:person.011504076050.36 schema:affiliation grid-institutes:None
    201 schema:familyName Rodrigues
    202 schema:givenName Nuno R.
    203 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011504076050.36
    204 rdf:type schema:Person
    205 sg:person.01231224052.28 schema:affiliation grid-institutes:grid.9983.b
    206 schema:familyName Jongen
    207 schema:givenName Marjan
    208 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01231224052.28
    209 rdf:type schema:Person
    210 sg:person.012560552411.84 schema:affiliation grid-institutes:grid.8389.a
    211 schema:familyName Serrano
    212 schema:givenName João
    213 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012560552411.84
    214 rdf:type schema:Person
    215 sg:person.01344743243.18 schema:affiliation grid-institutes:None
    216 schema:familyName Gama
    217 schema:givenName Ivo
    218 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01344743243.18
    219 rdf:type schema:Person
    220 sg:person.01354645302.63 schema:affiliation grid-institutes:grid.9983.b
    221 schema:familyName Domingos
    222 schema:givenName Tiago
    223 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01354645302.63
    224 rdf:type schema:Person
    225 sg:person.015750134410.90 schema:affiliation grid-institutes:grid.9983.b
    226 schema:familyName Tufik
    227 schema:givenName Camila
    228 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015750134410.90
    229 rdf:type schema:Person
    230 sg:person.0637362650.44 schema:affiliation grid-institutes:grid.9983.b
    231 schema:familyName Teixeira
    232 schema:givenName Ricardo F.M.
    233 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0637362650.44
    234 rdf:type schema:Person
    235 sg:person.0661045224.15 schema:affiliation grid-institutes:grid.9983.b
    236 schema:familyName Fangueiro
    237 schema:givenName David
    238 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0661045224.15
    239 rdf:type schema:Person
    240 sg:pub.10.1007/s10344-021-01486-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1137145014
    241 https://doi.org/10.1007/s10344-021-01486-2
    242 rdf:type schema:CreativeWork
    243 sg:pub.10.1007/s10705-005-5769-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1005778597
    244 https://doi.org/10.1007/s10705-005-5769-z
    245 rdf:type schema:CreativeWork
    246 sg:pub.10.1007/s11119-011-9251-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013175984
    247 https://doi.org/10.1007/s11119-011-9251-4
    248 rdf:type schema:CreativeWork
    249 sg:pub.10.1007/s11119-012-9274-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020655667
    250 https://doi.org/10.1007/s11119-012-9274-5
    251 rdf:type schema:CreativeWork
    252 sg:pub.10.1007/s11119-015-9419-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036395932
    253 https://doi.org/10.1007/s11119-015-9419-4
    254 rdf:type schema:CreativeWork
    255 sg:pub.10.1007/s11119-018-9592-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1105803503
    256 https://doi.org/10.1007/s11119-018-9592-3
    257 rdf:type schema:CreativeWork
    258 sg:pub.10.1007/s11119-020-09708-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1124280830
    259 https://doi.org/10.1007/s11119-020-09708-4
    260 rdf:type schema:CreativeWork
    261 sg:pub.10.1007/s11119-021-09806-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1137371122
    262 https://doi.org/10.1007/s11119-021-09806-x
    263 rdf:type schema:CreativeWork
    264 sg:pub.10.1007/s11119-021-09827-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1138950866
    265 https://doi.org/10.1007/s11119-021-09827-6
    266 rdf:type schema:CreativeWork
    267 sg:pub.10.1007/s11258-011-9931-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024905558
    268 https://doi.org/10.1007/s11258-011-9931-1
    269 rdf:type schema:CreativeWork
    270 sg:pub.10.1007/s13762-015-0750-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036376145
    271 https://doi.org/10.1007/s13762-015-0750-0
    272 rdf:type schema:CreativeWork
    273 sg:pub.10.1007/s40333-013-0180-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009845820
    274 https://doi.org/10.1007/s40333-013-0180-0
    275 rdf:type schema:CreativeWork
    276 sg:pub.10.1038/s41558-018-0081-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101086651
    277 https://doi.org/10.1038/s41558-018-0081-5
    278 rdf:type schema:CreativeWork
    279 sg:pub.10.1038/s41586-020-2649-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1130863323
    280 https://doi.org/10.1038/s41586-020-2649-2
    281 rdf:type schema:CreativeWork
    282 sg:pub.10.1038/s41598-019-43330-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1113875044
    283 https://doi.org/10.1038/s41598-019-43330-3
    284 rdf:type schema:CreativeWork
    285 sg:pub.10.1186/s13007-022-00866-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1146074958
    286 https://doi.org/10.1186/s13007-022-00866-2
    287 rdf:type schema:CreativeWork
    288 grid-institutes:None schema:alternateName Terraprima – Serviços Ambientais, Sociedade Unipessoal, Lda, 2135-199, Samora Correia, Portugal
    289 schema:name Terraprima – Serviços Ambientais, Sociedade Unipessoal, Lda, 2135-199, Samora Correia, Portugal
    290 rdf:type schema:Organization
    291 grid-institutes:grid.8389.a schema:alternateName Mediterranean Institute for Agriculture, Environment and Development (MED), Universidade de Évora, P.O. Box 94, 7002-554, Évora, Portugal
    292 schema:name Mediterranean Institute for Agriculture, Environment and Development (MED), Universidade de Évora, P.O. Box 94, 7002-554, Évora, Portugal
    293 rdf:type schema:Organization
    294 grid-institutes:grid.9983.b schema:alternateName Centro de Estudos Florestais (CEF), Instituto Superior de Agronomia, Universidade de Lisboa, Tapada da Ajuda, 1349-017, Lisboa, Portugal
    295 IDMEC - Mechanical Engineering Institute, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1, 1049-001, Lisbon, Portugal
    296 Linking Landscape, Environment, Agriculture and Food (LEAF), Instituto Superior de Agronomia, Universidade de Lisboa, Tapada da Ajuda, 1349-017, Lisboa, Portugal
    297 MARETEC – Marine, Environment and Technology Centre, LARSyS, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1, 1049-001, Lisboa, Portugal
    298 schema:name Centro de Estudos Florestais (CEF), Instituto Superior de Agronomia, Universidade de Lisboa, Tapada da Ajuda, 1349-017, Lisboa, Portugal
    299 IDMEC - Mechanical Engineering Institute, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1, 1049-001, Lisbon, Portugal
    300 Linking Landscape, Environment, Agriculture and Food (LEAF), Instituto Superior de Agronomia, Universidade de Lisboa, Tapada da Ajuda, 1349-017, Lisboa, Portugal
    301 MARETEC – Marine, Environment and Technology Centre, LARSyS, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1, 1049-001, Lisboa, Portugal
    302 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...