High Resolution Planetscope Imagery and Machine Learning for Estimating Suspended Particulate Matter

Ebinur Lake is a shallow lake and vulnerable to strong winds, which can lead to drastic changes in suspended particulate matter (SPM). High spatial and temporal resolution images are therefore urgently needed for SPM monitoring over the Ebinur Lake. Hence, a high-efficiency inversion model of estimating SPM from high-resolution images using machine learning is essential to increase the amount of extracted information through band combinations quadratic optimization. This article aims to evaluate the capability of the PlanetScope images and four machine learning approaches for estimating SPM of the Ebinur Lake. The specific objectives include: to obtain the sensitive bands and band combinations for SPM using correlation analysis; to quadratically optimize the combination pattern of sensitive bands using a linear model; and to compare the accuracy of traditional linear model and machine learning models in estimating SPM. The results of the study confirm that after linear model quadratic optimization, the band combinations of B3*B4, (B2+B3)/ (B2-B3), (B3+B4)*(B3+B4), and (B3-B2)/(B2/B3) have higher accuracy than that of the single band model. By inputting the preferred four-band combinations into the partial least squares, random forest, extreme gradient boosting, gradient boosting decision tree, and categorical boosting (CatBoost) models, the performance of the SPM inversion based on PlanetScope images is better than the traditional linear model. Validation of the inversion maps with observations further indicates that the CatBoost model performed the best.