Laboratory for
Climatology and Remote Sensing

Abstract:

A new satellite-based algorithm for rainfall retrieval in high spatio-temporal resolution fo Ecuador is presented. The algorithm relies on the precipitation information from the Integrated Multi-SatEllite Retrieval for the Global Precipitation Measurement (GPM) (IMERG) and infrared (IR) data from the Geostationary Operational Environmental Satellite-16 (GOES-16). It wa developed to (i) classify the rainfall area (ii) assign the rainfall rate. In each step, we selected the most important predictors and hyperparameter tuning parameters monthly. Between 19 April 2017 and 30 November 2017, brightness temperature derived from the GOES-16 IR channels and ancillary geo-information were trained with microwave-only IMERG-V06 using random forest (RF). Validation was done against independent microwave-only IMERG-V06 information not used for training. The validation results showed the new rainfall retrieva technique (multispectral) outperforms the IR-only IMERG rainfall product. This offers using the multispectral IR data can improve the retrieval performance compared to single-spectrum IR approaches. The standard verification scored a median Heidke skill score of ~0.6 for the rain area delineation and R between ~0.5 and ~0.62 for the rainfall rate assignment, indicating uncertainties for Andes’s high elevation. Comparison of RF rainfall rates in 2 km2 resolution with daily rain gauge measurements reveals the correlation of R = ~0.33.

Abstract:

The Random Forest (RF) algorithm, a decision-tree-based technique, has become a promising approach for applications addressing runoff forecasting in remote areas. This machine learning approach can overcome the limitations of scarce spatio-temporal data and physical parameters needed for process-based hydrological models. However, the influence of RF hyperparameters is still uncertain and needs to be explored. Therefore, the aim of this study is to analyze the sensitivity of RF runoff forecasting models of varying lead time to the hyperparameters of the algorithm. For this, models were trained by using (a) default and (b) extensive hyperparameter combinations through a grid-search approach that allow reaching the optimal set. Model performances were assessed based on the R2, %Bias, and RMSE metrics. We found that: (i) The most influencing hyperparameter is the number of trees in the forest, however the combination of the depth of the tree and the number of features hyperparameters produced the highest variability-instability on the models. (ii) Hyperparameter optimization significantly improved model performance for higher lead times (12- and 24-h). For instance, the performance of the 12-h forecasting model under default RF hyperparameters improved to R2 = 0.41 after optimization (gain of 0.17). However, for short lead times (4-h) there was no significant model improvement (0.69 < R2 < 0.70). (iii) There is a range of values for each hyperparameter in which the performance of the model is not significantly affected but remains close to the optimal. Thus, a compromise between hyperparameter interactions (i.e., their values) can produce similar high model performances. Model improvements after optimization can be explained from a hydrological point of view, the generalization ability for lead times larger than the concentration time of the catchment tend to rely more on hyperparameterization than in what they can learn from the input data. This insight can help in the development of operational early warning systems

Abstract:

A new satellite-based technique for rainfall retrieval in high spatio-temporal resolution (3 km, 15 min) for Iran is presented. The algorithm is based on the infrared bands of the Meteosat Second Generation Spinning Enhanced Visible and Infrared Imager (MSG SEVIRI). Random forest models using microwave-only rainfall information of the Integrated Multi-SatEllite Retrieval for the Global Precipitation Measurement (GPM) (IMERG) product as a reference were developed to (i) delineate the rainfall area and (ii) to assign the rainfall rate. The method was validated against independent microwave-only GPM IMERG rainfall data not used for model training. Additionally, the new technique was validated against completely independent gauge station data. The validation results show a promising performance of the new rainfall retrieval technique, especially when compared to the GPM IMERG IR-only rainfall product. The standard verification scored an average Heidke Skill Score of 0.4 for rain area delineation and an average R between 0.1 and 0.7 for rainfall rate assignment, indicating uncertainties for the Lut Desert area and regions with high altitude gradients.

Abstract:

Despite many eorts of the radar community, quantitative precipitation estimation (QPE) from weather radar data remains a challenging topic. The high resolution of X-band radar imagery in space and time comes with an intricate correction process of reflectivity. The steep and high mountain topography of the Andes enhances its complexity. This study aims to optimize the rainfall derivation of the highest X-band radar in the world (4450 m a.s.l.) by using a random forest (RF) model and single Plan Position Indicator (PPI) scans. The performance of the RFmodel was evaluated in comparison with the traditional step-wise approach by using both, the Marshall-Palmer and a site-specific Z–R relationship. Since rain gauge networks are frequently unevenly distributed and hardly available at real time in mountain regions, bias adjustment was neglected. Results showed an improvement in the step-wise approach by using the site-specific (instead of the Marshall-Palmer) Z–R relationship. However, both models highly underestimate the rainfall rate (correlation coecient < 0.69; slope up to 12). Contrary, the RF model greatly outperformed the step-wise approach in all testing locations and on dierent rainfall events (correlation coecient up to 0.83; slope = 1.04). The results are promising and unveil a dierent approach to overcome the high attenuation issues inherent to X-band radars.

Abstract:

Up until now montane cloud forest (MCF) in Taiwan has only been mapped for selected areas of vegetation plots. This paper presents the first comprehensive map of MCF distribution for the entire island. For its creation, a Random Forest model was trained with vegetation plots from the National Vegetation Database of Taiwan that were classified as “MCF” or “non-MCF”. This model predicted the distribution of MCF from a raster data set of parameters derived from a digital elevation model (DEM), Landsat channels and texture measures derived from them as well as ground fog frequency data derived from the Moderate Resolution Imaging Spectroradiometer. While the DEM parameters and Landsat data predicted much of the cloud forest’s location, local deviations in the altitudinal distribution of MCF linked to the monsoonal influence as well as the Massenerhebung effect (causing MCF in atypically low altitudes) were only captured once fog frequency data was included. Therefore, our study suggests that ground fog data are most useful for accurately mapping MCF.

Abstract:

Though the relevance of pasture degradation on the Qinghai-Tibet Plateau (QTP) is widely postulated, its extent is still unknown. Due to the enormous spatial extent, remote sensing provides the only possibility to investigate pasture degradation via frequently used proxies such as vegetation cover and aboveground biomass (AGB). However, unified remote sensing approaches are still lacking. This study tests the appli- cability of hyper- and multispectral in situ measurements to map vegetation cover and AGB on regional scales. Using machine learning techniques, it is tested whether the full hyperspectral information is needed or if multispectral information is sufficient to accurately estimate pasture degradation prox- ies. To regionalize pasture degradation proxies, the transferability of the locally derived ML-models to high resolution multispectral satellite data is assessed. 1183 hyperspectral measurements and vegeta- tion records were performed at 18 locations on the QTP. Random Forests models with recursive feature selection were trained to estimate vegetation cover and AGB using narrow-band indices (NBI) as predic- tors. Separate models were calculated using NBI from hyperspectral data as well as from the same data resampled to WorldView-2, QuickBird and RapidEye channels. The hyperspectral results were compared to the multispectral results. Finally, the models were applied to satellite data to map vegetation cover and AGB on a regional scale. Vegetation cover was accurately predicted by Random Forest if hyperspectral measurements were used (cross validated R2 = 0.89). In contrast, errors in AGB estimations were consid- erably higher (cross validated R2 = 0.32). Only small differences in accuracy were observed between the models based on hyperspectral compared to multispectral data. The application of the models to satellite images generally resulted in an increase of the estimation error. Though this reflects the challenge of applying in situ measurements to satellite data, the results still show a high potential to map pasture degradation proxies on the QTP. Thus, this study presents robust methodology to remotely detect and monitor pasture degradation at high spatial resolutions.

Abstract:

The present study aims to investigate the potential of the random forests ensemble classification and regression technique to improve rainfall rate assignment during day, night and twilight (resulting in 24-hour precipitation estimates) based on cloud physical properties retrieved from Meteosat Second Generation (MSG) Spinning Enhanced Visible and InfraRed Imager (SEVIRI) data. Random forests (RF) models contain a combination of characteristics that make them well suited for its application in precipitation remote sensing. One of the key advantages is the ability to capture non-linear association of patterns between predictors and response which becomes important when dealing with complex non-linear events like precipitation. Due to the deficiencies of existing optical rainfall retrievals, the focus of this study is on assigning rainfall rates to precipitating cloud areas in connection with extra-tropical cyclones in mid-latitudes including both convective and advective-stratiform precipitating cloud areas. Hence, the rainfall rates are assigned to rain areas previously identified and classified according to the precipitation formation processes. As predictor variables water vapor-IR differences and IR cloud top temperature are used to incorporate information on cloud top height. ?T8.7–10.8 and ?T10.8–12.1 are considered to supply information about the cloud phase. Furthermore, spectral SEVIRI channels (VIS0.6, VIS0.8, NIR1.6) and cloud properties (cloud effective radius, cloud optical thickness) are used to include information about the cloud water path during daytime, while suitable combinations of temperature differences (?T3.9–10.8, ?T3.9–7.3) are considered during night-time. The development of the rainfall rate retrieval technique is realised in three steps. First, an extensive tuning study is carried out to customise each of the RF models. The daytime, night-time and twilight precipitation events have to be treated separately due to differing information content about the cloud properties between the different times of day. Secondly, the RF models are trained using the optimum values for the number of trees and number of randomly chosen predictor variables found in the tuning study. Finally, the final RF models are used to predict rainfall rates using an independent validation data set and the results are validated against co-located rainfall rates observed by a ground radar network. To train and validate the model, the radar-based RADOLAN RW product from the German Weather Service (DWD) is used which provides area-wide gauge-adjusted hourly precipitation information. Regarding the overall performance, as indicated by the coefficient of determination (Rsq), hourly rainfall rates show already a good correlation with Rsq = 0.5 (day and night) and Rsq = 0.48 (twilight) between the satellite and radar based observations. Higher temporal aggregation leads to better agreement. Rsq rises to 0.78 (day), 0.77 (night) and 0.75 (twilight) for 8-h interval. By comparing day, night and twilight performance it becomes evident that daytime precipitation is generally predicted best by the model. Twilight and night-time predictions are generally less accurate but only by a small margin. This may due to the smaller number of predictor variables during twilight and night-time conditions as well as less favourable radiative transfer conditions to obtain the cloud parameters during these periods. However, the results show that with the newly developed method it is possible to assign rainfall rates with good accuracy even on an hourly basis. Furthermore, the rainfall rates can be assigned during day, night and twilight conditions which enables the estimation of rainfall rates 24 h day.