Assessing Machine Learning Models for Gap Filling Daily Rainfall Series in a Semiarid Region of Spain
Assessing Machine Learning Models for Gap Filling Daily Rainfall Series in a Semiarid Region of Spain
复制标题
DOI：
10.3390/atmos12091158
复制
发表时间：
2021-09-01
期刊：
影响因子：
2.9
通讯作者：
Penelope Garcia-Marin, Amanda
中科院分区：
文献类型：
--
作者：
Antonio Bellido-Jimenez, Juan;Estevez Gualda, Javier;Penelope Garcia-Marin, Amanda
水文气象数据集中数据缺失是一个常见问题，通常是由于传感器故障、记录存储和传输缺陷或其他恢复程序问题造成的。在分析和建模其空间和时间变化时，这些缺失值是问题的主要根源。因此，需要准确的降雨时间序列填补技术来获得完整的数据集，这对于研究气候变化演化至关重要。在这项工作中，使用不同的方法和安达卢西亚（西班牙南部）半干旱地区的位置，评估了几种机器学习模型来填补降雨数据的缺口。根据获得的结果，使用位于 50 公里半径内的邻居数据的性能远远优于其他评估方法，RMSE（均方根误差）值高达 1.246 毫米/天，MBE（平均偏差误差）值高达 -0.001 毫米/天，R-2 值高达 0.898。此外，内陆地区的结果在大多数地方都优于沿海地区，产生了基于距海距离的效率效应（RMSE 提高了 63.89%）。最后，机器学习 (ML) 模型（尤其是 MLP（多层感知器））在沿海地区的表现明显优于简单线性回归估计，而在内陆地区，改进并不那么显着。
The presence of missing data in hydrometeorological datasets is a common problem, usually due to sensor malfunction, deficiencies in records storage and transmission, or other recovery procedures issues. These missing values are the primary source of problems when analyzing and modeling their spatial and temporal variability. Thus, accurate gap-filling techniques for rainfall time series are necessary to have complete datasets, which is crucial in studying climate change evolution. In this work, several machine learning models have been assessed to gap-fill rainfall data, using different approaches and locations in the semiarid region of Andalusia (Southern Spain). Based on the obtained results, the use of neighbor data, located within a 50 km radius, highly outperformed the rest of the assessed approaches, with RMSE (root mean squared error) values up to 1.246 mm/day, MBE (mean bias error) values up to -0.001 mm/day, and R-2 values up to 0.898. Besides, inland area results outperformed coastal area in most locations, arising the efficiency effects based on the distance to the sea (up to an improvement of 63.89% in terms of RMSE). Finally, machine learning (ML) models (especially MLP (multilayer perceptron)) notably outperformed simple linear regression estimations in the coastal sites, whereas in inland locations, the improvements were not such significant.