A genetic algorithm‐based stacking algorithm for predicting soil organic matter from vis–NIR spectral data

• Published in: European journal of soil science Vol. 70; no. 3; pp. 578 - 590
• Main Authors: Tsakiridis, Nikolaos L., Tziolas, Nikolaos V., Theocharis, John B., Zalidis, George C.
• Format: Journal Article
• Language: English
• Published: Oxford, UK Blackwell Publishing Ltd 01.05.2019; Wiley Subscription Services, Inc
• Subjects: Algorithms; Analytical methods; Balkans; Diffuse reflectance spectroscopy; Genetic algorithms; GEO‐CRADLE; Mathematical models; Middle East; model stacking; North Africa; Organic chemistry; Organic matter; Permutations; prediction; Predictions; Reflectance; reflectance spectroscopy; Soil chemistry; Soil organic matter; Soil properties; soil spectroscopy; Spectra; spectral analysis; Spectroscopy; Stacking; vis–NIR spectroscopy
• ISSN: 1351-0754; 1365-2389
• DOI: 10.1111/ejss.12760

It has been demonstrated that diffuse reflectance spectroscopy in the visible and near‐infrared (vis–NIR) can be exploited to predict chemical and physical soil properties. Immense soil spectral libraries (SSL) are being developed; therefore, more elaborate tools that capitalize on contemporary knowledge and techniques need to be established to provide accurate predictions. In this paper, we propose a novel genetic algorithm‐based stacking model that makes synergetic use of multiple models developed from different preprocessed spectral sources (termed L1 models). This is a form of ensemble learning where multiple hypotheses are combined to create a more robust and more accurate ensemble hypothesis. The genetic algorithm automatically defines the configuration of the stacked model, by selecting the best cooperating subset of the initial models. Our methodology was tested on the newly developed GEO‐CRADLE SSL to predict soil organic matter (SOM). Results showed that the accuracy of prediction of the proposed method ( R2 = 0.76, and ratio of performance to interquartile range [RPIQ] = 2.22) was better than the one attained by the best L1 model ( R2 = 0.65, RPIQ = 1.93). This approach can thus be effectively utilized to enhance the predictions of soil properties in small and large soil spectral libraries alike. Highlights A novel model stacking algorithm is proposed, combining spectral models from different sources and algorithms. Use of a genetic algorithm is examined, accounting for the large number of possible model permutations. The methodology was applied to the GEO‐CRADLE vis–NIR soil spectral library. Results indicate that model stacking creates more accurate and robust models.