@article{SteiningerAbelZiegleretal.2023, author = {Steininger, Michael and Abel, Daniel and Ziegler, Katrin and Krause, Anna and Paeth, Heiko and Hotho, Andreas}, title = {ConvMOS: climate model output statistics with deep learning}, series = {Data Mining and Knowledge Discovery}, volume = {37}, journal = {Data Mining and Knowledge Discovery}, number = {1}, issn = {1384-5810}, doi = {10.1007/s10618-022-00877-6}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-324213}, pages = {136-166}, year = {2023}, abstract = {Climate models are the tool of choice for scientists researching climate change. Like all models they suffer from errors, particularly systematic and location-specific representation errors. One way to reduce these errors is model output statistics (MOS) where the model output is fitted to observational data with machine learning. In this work, we assess the use of convolutional Deep Learning climate MOS approaches and present the ConvMOS architecture which is specifically designed based on the observation that there are systematic and location-specific errors in the precipitation estimates of climate models. We apply ConvMOS models to the simulated precipitation of the regional climate model REMO, showing that a combination of per-location model parameters for reducing location-specific errors and global model parameters for reducing systematic errors is indeed beneficial for MOS performance. We find that ConvMOS models can reduce errors considerably and perform significantly better than three commonly used MOS approaches and plain ResNet and U-Net models in most cases. Our results show that non-linear MOS models underestimate the number of extreme precipitation events, which we alleviate by training models specialized towards extreme precipitation events with the imbalanced regression method DenseLoss. While we consider climate MOS, we argue that aspects of ConvMOS may also be beneficial in other domains with geospatial data, such as air pollution modeling or weather forecasts.}, subject = {Klima}, language = {en} } @article{WeismannMoeckelPaethetal.2023, author = {Weismann, Dirk and M{\"o}ckel, Martin and Paeth, Heiko and Slagman, Anna}, title = {Modelling variations of emergency attendances using data on community mobility, climate and air pollution}, series = {Scientific Reports}, volume = {13}, journal = {Scientific Reports}, doi = {10.1038/s41598-023-47857-4}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-357578}, year = {2023}, abstract = {Air pollution is associated with morbidity and mortality worldwide. We investigated the impact of improved air quality during the economic lockdown during the SARS-Cov2 pandemic on emergency room (ER) admissions in Germany. Weekly aggregated clinical data from 33 hospitals were collected in 2019 and 2020. Hourly concentrations of nitrogen and sulfur dioxide (NO2, SO2), carbon and nitrogen monoxide (CO, NO), ozone (O3) and particulate matter (PM10, PM2.5) measured by ground stations and meteorological data (ERA5) were selected from a 30 km radius around the corresponding ED. Mobility was assessed using aggregated cell phone data. A linear stepwise multiple regression model was used to predict ER admissions. The average weekly emergency numbers vary from 200 to over 1600 cases (total n = 2,216,217). The mean maximum decrease in caseload was 5 standard deviations. With the enforcement of the shutdown in March, the mobility index dropped by almost 40\%. Of all air pollutants, NO2 has the strongest correlation with ER visits when averaged across all departments. Using a linear stepwise multiple regression model, 63\% of the variation in ER visits is explained by the mobility index, but still 6\% of the variation is explained by air quality and climate change.}, language = {en} } @article{LibandaPaeth2023, author = {Libanda, Brigadier and Paeth, Heiko}, title = {Modelling wind speed across Zambia: Implications for wind energy}, series = {International Journal of Climatology}, volume = {43}, journal = {International Journal of Climatology}, number = {2}, doi = {10.1002/joc.7826}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-312134}, pages = {772 -- 786}, year = {2023}, abstract = {Wind energy is a key option in global dialogues about climate change mitigation. Here, we combined observations from surface wind stations, reanalysis datasets, and state-of-the-art regional climate models from the Coordinated Regional Climate Downscaling Experiment (CORDEX Africa) to study the current and future wind energy potential in Zambia. We found that winds are dominated by southeasterlies and are rarely strong with an average speed of 2.8 m·s\(^{-1}\). When we converted the observed surface wind speed to a turbine hub height of 100 m, we found a ~38\% increase in mean wind speed for the period 1981-2000. Further, both simulated and observed wind speed data show statistically significant increments across much of the country. The only areas that divert from this upward trend of wind speeds are the low land terrains of the Eastern Province bordering Malawi. Examining projections of wind power density (WPD), we found that although wind speed is increasing, it is still generally too weak to support large-scale wind power generation. We found a meagre projected annual average WPD of 46.6 W·m\(^{-2}\). The highest WPDs of ~80 W·m\(^{-2}\) are projected in the northern and central parts of the country while the lowest are to be expected along the Luangwa valley in agreement with wind speed simulations. On average, Zambia is expected to experience minor WPD increments of 0.004 W·m\(^{-2}\) per year from 2031 to 2050. We conclude that small-scale wind turbines that accommodate cut-in wind speeds of 3.8 m·s\(^{-1}\) are the most suitable for power generation in Zambia. Further, given the limitations of small wind turbines, they are best suited for rural and suburban areas of the country where obstructions are few, thus making them ideal for complementing the government of the Republic of Zambia's rural electrification efforts.}, language = {en} }