The atmospheric boundary layer height (BLH) is a key parameter for many meteorological applications, including air quality forecasts. Several algorithms have been proposed to automatically estimate BLH from lidar backscatter profiles. However recent advances in computing have enabled new approaches using machine learning that are seemingly well suited to this problem. Machine learning can handle complex classification problems and can be trained by a human expert. This paper describes and compares two machine-learning methods, the K-means unsupervised algorithm and the AdaBoost supervised algorithm, to derive BLH from lidar backscatter profiles. The K-means for Atmospheric Boundary Layer (KABL) and AdaBoost for Atmospheric Boundary Layer (ADABL) algorithm codes used in this study are free and open source. Both methods were compared to reference BLHs derived from colocated radiosonde data over a 2-year period (2017–2018) at two Météo-France operational network sites (Trappes and Brest). A large discrepancy between the root-mean-square error (RMSE) and correlation with radiosondes was observed between the two sites. At the Trappes site, KABL and ADABL outperformed the manufacturer's algorithm, while the performance was clearly reversed at the Brest site. We conclude that ADABL is a promising algorithm (RMSE of 550 m at Trappes, 800 m for manufacturer) but has training issues that need to be resolved; KABL has a lower performance (RMSE of 800 m at Trappes) than ADABL but is much more versatile.

中文翻译：

---

使用机器学习从气溶胶激光雷达导出边界层高度：KABL 和 ADABL 算法

大气边界层高度 (BLH) 是许多气象应用（包括空气质量预测）的关键参数。已经提出了几种算法来根据激光雷达反向散射轮廓自动估计 BLH。然而，最近在计算方面的进步已经启用了使用机器学习的新方法，这些方法似乎非常适合这个问题。机器学习可以处理复杂的分类问题，并且可以由人类专家进行训练。本文描述并比较了两种机器学习方法，即K- means 无监督算法和 AdaBoost 监督算法，以从激光雷达反向散射剖面中推导出 BLH。该ķ-means for Atmospheric Boundary Layer (KABL) 和 AdaBoost for Atmospheric Boundary Layer (ADABL) 算法代码是免费和开源的。这两种方法都与法国气象局两个运营网络站点（特拉普斯和布雷斯特）在 2 年期间（2017-2018 年）的共址无线电探空仪数据中得出的参考 BLH 进行了比较。在两个站点之间观察到均方根误差 (RMSE) 和与无线电探空仪的相关性之间存在很大差异。在 Trappes 站点，KABL 和 ADABL 的性能优于制造商的算法，而在 Brest 站点的性能明显相反。我们得出结论，ADABL 是一种很有前途的算法（Trappes 的 RMSE 为 550 m，制造商为 800 m），但存在需要解决的训练问题；