To quickly and accurately ascertain the leaf area index (LAI) of breeding sunflowers, unmanned aerial vehicle (UAV) remote sensing data were collected at the budding, flowering, and maturation phases of the sunflowers by utilizing a multispectral camera and DJI L1 LiDAR lens. The analysis included the computation of nine multispectral vegetation indices and eight categories of texture features, alongside the extraction of eight LiDAR feature parameters. By applying the Pearson correlation coefficient method, four vegetation indices, three texture categories, and four LiDAR features, which exhibited a high correlation with LAI, were identified for further analysis.The study employed machine learning algorithms, namely K-nearest neighbor (KNN), random forest (RF), eXtreme gradient boosting (XGBoost), and category boosting (CatBoost), to develop models for estimating the LAI of sunflowers. These models were based on singular and combined inputs of vegetation indices, texture features, and LiDAR feature parameters. The accuracy of these models was evaluated by using the full terms coefficient of determination (R2) and root mean square error (RMSE). The model that showcased the highest accuracy, utilizing the CatBoost algorithm in conjunction with a combination of vegetation indices, texture features, and LiDAR feature parameters, was selected for inverse estimation of LAI in breeding sunflowers and subsequent visualization. The findings demonstrated that this combined approach yielded the best model for LAI estimation across all three stages of sunflower growth, with coefficient of determination values of 0.93, 0.91 and 0.90, and root mean square error values of 0.13, 0.14 and 0.15, respectively. The research result can lay the groundwork for enhanced sunflower breeding and precise field management by leveraging advanced remote sensing and machine learning technologies.