A hybrid training approach for leaf area index estimation via Cubist and random forests machine-learning

Handle URI:
http://hdl.handle.net/10754/626588
Title:
A hybrid training approach for leaf area index estimation via Cubist and random forests machine-learning
Authors:
McCabe, Matthew ( 0000-0002-1279-5272 ) ; McCabe, Matthew ( 0000-0002-1279-5272 )
Abstract:
With an increasing volume and dimensionality of Earth observation data, enhanced integration of machine-learning methodologies is needed to effectively analyze and utilize these information rich datasets. In machine-learning, a training dataset is required to establish explicit associations between a suite of explanatory ‘predictor’ variables and the target property. The specifics of this learning process can significantly influence model validity and portability, with a higher generalization level expected with an increasing number of observable conditions being reflected in the training dataset. Here we propose a hybrid training approach for leaf area index (LAI) estimation, which harnesses synergistic attributes of scattered in-situ measurements and systematically distributed physically based model inversion results to enhance the information content and spatial representativeness of the training data. To do this, a complimentary training dataset of independent LAI was derived from a regularized model inversion of RapidEye surface reflectances and subsequently used to guide the development of LAI regression models via Cubist and random forests (RF) decision tree methods. The application of the hybrid training approach to a broad set of Landsat 8 vegetation index (VI) predictor variables resulted in significantly improved LAI prediction accuracies and spatial consistencies, relative to results relying on in-situ measurements alone for model training. In comparing the prediction capacity and portability of the two machine-learning algorithms, a pair of relatively simple multi-variate regression models established by Cubist performed best, with an overall relative mean absolute deviation (rMAD) of ∼11%, determined based on a stringent scene-specific cross-validation approach. In comparison, the portability of RF regression models was less effective (i.e., an overall rMAD of ∼15%), which was attributed partly to model saturation at high LAI in association with inherent extrapolation and transferability limitations. Explanatory VIs formed from bands in the near-infrared (NIR) and shortwave infrared domains (e.g., NDWI) were associated with the highest predictive ability, whereas Cubist models relying entirely on VIs based on NIR and red band combinations (e.g., NDVI) were associated with comparatively high uncertainties (i.e., rMAD ∼21%). The most transferable and best performing models were based on combinations of several predictor variables, which included both NDWI- and NDVI-like variables. In this process, prior screening of input VIs based on an assessment of variable relevance served as an effective mechanism for optimizing prediction accuracies from both Cubist and RF. While this study demonstrated benefit in combining data mining operations with physically based constraints via a hybrid training approach, the concept of transferability and portability warrants further investigations in order to realize the full potential of emerging machine-learning techniques for regression purposes.
KAUST Department:
Biological and Environmental Sciences and Engineering (BESE) Division; Water Desalination and Reuse Research Center (WDRC)
Citation:
Houborg R, McCabe MF (2018) A hybrid training approach for leaf area index estimation via Cubist and random forests machine-learning. ISPRS Journal of Photogrammetry and Remote Sensing 135: 173–188. Available: http://dx.doi.org/10.1016/j.isprsjprs.2017.10.004.
Publisher:
Elsevier BV
Journal:
ISPRS Journal of Photogrammetry and Remote Sensing
Issue Date:
6-Dec-2017
DOI:
10.1016/j.isprsjprs.2017.10.004
Type:
Article
ISSN:
0924-2716
Sponsors:
Research reported in this publication was supported by the King Abdullah University of Science and Technology (KAUST). We greatly appreciate the logistical, equipment and scientific support offered to our team by Mr Jack King, Mr Alan King and employees of the Tawdeehiya Farm in Al Kharj, Saudi Arabia, without whom this research would not have been possible.
Additional Links:
http://www.sciencedirect.com/science/article/pii/S0924271617303209
Appears in Collections:
Articles; Water Desalination and Reuse Research Center (WDRC); Biological and Environmental Sciences and Engineering (BESE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorMcCabe, Matthewen
dc.contributor.authorMcCabe, Matthewen
dc.date.accessioned2018-01-01T12:19:01Z-
dc.date.available2018-01-01T12:19:01Z-
dc.date.issued2017-12-06en
dc.identifier.citationHouborg R, McCabe MF (2018) A hybrid training approach for leaf area index estimation via Cubist and random forests machine-learning. ISPRS Journal of Photogrammetry and Remote Sensing 135: 173–188. Available: http://dx.doi.org/10.1016/j.isprsjprs.2017.10.004.en
dc.identifier.issn0924-2716en
dc.identifier.doi10.1016/j.isprsjprs.2017.10.004en
dc.identifier.urihttp://hdl.handle.net/10754/626588-
dc.description.abstractWith an increasing volume and dimensionality of Earth observation data, enhanced integration of machine-learning methodologies is needed to effectively analyze and utilize these information rich datasets. In machine-learning, a training dataset is required to establish explicit associations between a suite of explanatory ‘predictor’ variables and the target property. The specifics of this learning process can significantly influence model validity and portability, with a higher generalization level expected with an increasing number of observable conditions being reflected in the training dataset. Here we propose a hybrid training approach for leaf area index (LAI) estimation, which harnesses synergistic attributes of scattered in-situ measurements and systematically distributed physically based model inversion results to enhance the information content and spatial representativeness of the training data. To do this, a complimentary training dataset of independent LAI was derived from a regularized model inversion of RapidEye surface reflectances and subsequently used to guide the development of LAI regression models via Cubist and random forests (RF) decision tree methods. The application of the hybrid training approach to a broad set of Landsat 8 vegetation index (VI) predictor variables resulted in significantly improved LAI prediction accuracies and spatial consistencies, relative to results relying on in-situ measurements alone for model training. In comparing the prediction capacity and portability of the two machine-learning algorithms, a pair of relatively simple multi-variate regression models established by Cubist performed best, with an overall relative mean absolute deviation (rMAD) of ∼11%, determined based on a stringent scene-specific cross-validation approach. In comparison, the portability of RF regression models was less effective (i.e., an overall rMAD of ∼15%), which was attributed partly to model saturation at high LAI in association with inherent extrapolation and transferability limitations. Explanatory VIs formed from bands in the near-infrared (NIR) and shortwave infrared domains (e.g., NDWI) were associated with the highest predictive ability, whereas Cubist models relying entirely on VIs based on NIR and red band combinations (e.g., NDVI) were associated with comparatively high uncertainties (i.e., rMAD ∼21%). The most transferable and best performing models were based on combinations of several predictor variables, which included both NDWI- and NDVI-like variables. In this process, prior screening of input VIs based on an assessment of variable relevance served as an effective mechanism for optimizing prediction accuracies from both Cubist and RF. While this study demonstrated benefit in combining data mining operations with physically based constraints via a hybrid training approach, the concept of transferability and portability warrants further investigations in order to realize the full potential of emerging machine-learning techniques for regression purposes.en
dc.description.sponsorshipResearch reported in this publication was supported by the King Abdullah University of Science and Technology (KAUST). We greatly appreciate the logistical, equipment and scientific support offered to our team by Mr Jack King, Mr Alan King and employees of the Tawdeehiya Farm in Al Kharj, Saudi Arabia, without whom this research would not have been possible.en
dc.publisherElsevier BVen
dc.relation.urlhttp://www.sciencedirect.com/science/article/pii/S0924271617303209en
dc.subjectMachine-learningen
dc.subjectLAIen
dc.subjectCubisten
dc.subjectRandom forestsen
dc.subjectHybriden
dc.subjectREGFLECen
dc.titleA hybrid training approach for leaf area index estimation via Cubist and random forests machine-learningen
dc.typeArticleen
dc.contributor.departmentBiological and Environmental Sciences and Engineering (BESE) Divisionen
dc.contributor.departmentWater Desalination and Reuse Research Center (WDRC)en
dc.identifier.journalISPRS Journal of Photogrammetry and Remote Sensingen
dc.contributor.institutionGeospatial Sciences Center of Excellence, South Dakota State University, Brookings, SD 57007-3510, USAen
kaust.authorMcCabe, Matthewen
kaust.authorMcCabe, Matthewen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.