Table 1 Training and test scores for regression analyses of leaf area index (LAI) with respect to climate factors using 10 machine learning (ML) regressors for rice in Cheorwon and Paju, South Korea.

From: Incorporation of machine learning and deep neural network approaches into a remote sensing-integrated crop model for the simulation of rice growth

Regressor

Cheorwon

Paju

Training score

Test score

Training score

Test score

Polynomial linear

0.498

0.490

0.427

0.417

Ridge

0.498

0.490

0.427

0.417

Lasso

0.441

0.428

0.426

0.416

Support vector

0.513

0.500

0.475

0.459

Random forest

0.843

0.622

0.828

0.568

Extra trees

0.863

0.590

0.855

0.489

Gradient boosting

0.549

0.543

0.508

0.499

HGB

0.611

0.590

0.579

0.551

XGB

0.671

0.613

0.650

0.561

LightGBM

0.612

0.590

0.580

0.552

  1. HGB, XGB, and LightGBM stand for Histogram-based Gradient Boosting, Extreme Gradient Boosting, and Light Gradient Boosting machine regression.
Back to article page