@phdthesis{Steininger2023,
  author    = {Steininger, Michael},
  title     = {Deep Learning for Geospatial Environmental Regression},
  doi       = {10.25972/OPUS-31312},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-313121},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2023},
  abstract  = {Environmental issues have emerged especially since humans burned fossil fuels, which led to air pollution and climate change that harm the environment. These issues' substantial consequences evoked strong efforts towards assessing the state of our environment. Various environmental machine learning (ML) tasks aid these efforts. These tasks concern environmental data but are common ML tasks otherwise, i.e., datasets are split (training, validatition, test), hyperparameters are optimized on validation data, and test set metrics measure a model's generalizability. This work focuses on the following environmental ML tasks: Regarding air pollution, land use regression (LUR) estimates air pollutant concentrations at locations where no measurements are available based on measured locations and each location's land use (e.g., industry, streets). For LUR, this work uses data from London (modeled) and Zurich (measured). Concerning climate change, a common ML task is model output statistics (MOS), where a climate model's output for a study area is altered to better fit Earth observations and provide more accurate climate data. This work uses the regional climate model (RCM) REMO and Earth observations from the E-OBS dataset for MOS. Another task regarding climate is grain size distribution interpolation where soil properties at locations without measurements are estimated based on the few measured locations. This can provide climate models with soil information, that is important for hydrology. For this task, data from Lower Franconia is used. Such environmental ML tasks commonly have a number of properties: (i) geospatiality, i.e., their data refers to locations relative to the Earth's surface. (ii) The environmental variables to estimate or predict are usually continuous. (iii) Data can be imbalanced due to relatively rare extreme events (e.g., extreme precipitation). (iv) Multiple related potential target variables can be available per location, since measurement devices often contain different sensors. (v) Labels are spatially often only sparsely available since conducting measurements at all locations of interest is usually infeasible. These properties present challenges but also opportunities when designing ML methods for such tasks. In the past, environmental ML tasks have been tackled with conventional ML methods, such as linear regression or random forests (RFs). However, the field of ML has made tremendous leaps beyond these classic models through deep learning (DL). In DL, models use multiple layers of neurons, producing increasingly higher-level feature representations with growing layer depth. DL has made previously infeasible ML tasks feasible, improved the performance for many tasks in comparison to existing ML models significantly, and eliminated the need for manual feature engineering in some domains due to its ability to learn features from raw data. To harness these advantages for environmental domains it is promising to develop novel DL methods for environmental ML tasks. This thesis presents methods for dealing with special challenges and exploiting opportunities inherent to environmental ML tasks in conjunction with DL. To this end, the proposed methods explore the following techniques: (i) Convolutions as in convolutional neural networks (CNNs) to exploit reoccurring spatial patterns in geospatial data. (ii) Posing the problems as regression tasks to estimate the continuous variables. (iii) Density-based weighting to improve estimation performance for rare and extreme events. (iv) Multi-task learning to make use of multiple related target variables. (v) Semi-supervised learning to cope with label sparsity. Using these techniques, this thesis considers four research questions: (i) Can air pollution be estimated without manual feature engineering? This is answered positively by the introduction of the CNN-based LUR model MapLUR as well as the off-the-shelf LUR solution OpenLUR. (ii) Can colocated pollution data improve spatial air pollution models? Multi-task learning for LUR is developed for this, showing potential for improvements with colocated data. (iii) Can DL models improve the quality of climate model outputs? The proposed DL climate MOS architecture ConvMOS demonstrates this. Additionally, semi-supervised training of multilayer perceptrons (MLPs) for grain size distribution interpolation is presented, which can provide improved input data. (iv) Can DL models be taught to better estimate climate extremes? To this end, density-based weighting for imbalanced regression (DenseLoss) is proposed and applied to the DL architecture ConvMOS, improving climate extremes estimation. These methods show how especially DL techniques can be developed for environmental ML tasks with their special characteristics in mind. This allows for better models than previously possible with conventional ML, leading to more accurate assessment and better understanding of the state of our environment.},
  subject      = {Deep learning},
  language  = {en}
}
@phdthesis{Jawork2022,
  author    = {Jawork, Anna},
  title     = {Die Rolle von durch rhGM-CSF aktivierten Makrophagen bei der Immunabwehr von Glioblastomen im orthotopen C6-Tumormodell der Ratte},
  doi       = {10.25972/OPUS-27855},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-278550},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2022},
  abstract  = {Die Immunabwehr des Patienten stellt eine Schl{\"u}sselrolle bei der spontanen Tumorregression dar. Bisher z{\"a}hlten zytotoxische CD8-positive T Zellen und nat{\"u}rliche Killerzellen zu den wichtigsten zellul{\"a}ren Vertretern der Tumorkontrolle. Im Tierversuch konnte jedoch kein signifikanter Einfluss dieser Zellen auf die spontane Regression nachgewiesen werden. Allerdings fand sich eine hohe Anzahl an Makrophagen im Tumorgewebe. In vorangegangenen Untersuchungen zeigte sich bei der Depletion der Makrophagen mittels Clodronate im Tiermodell der Ratte ein deutlich gesteigertes Tumorwachstum. In der hier durchgef{\"u}hrten Versuchsreihe wurde nun der Einfluss von Makrophagen auf das Tumorwachstum orthotop implantierter C6-Glioblastomsph{\"a}roide betrachtet. Dabei wurden die Makrophagen durch den Granulozyten-Makrophagen Kolonie-stimulierenden Faktor (rhGM-CSF, Leukine) aktiviert. 29 SD-Ratten wurden C6-Gliom-Sph{\"a}roide orthotop implantiert. 20 der Tiere wurden jeden zweiten Tag mit 1µg/100g K{\"o}rpergewicht rhGSM-CSF s. c. behandelt. Neun Tiere dienten als Kontrollgruppe. Zur Verlaufsbeurteilung wurden an den Tagen 7, 14, 21, 28, 32 und 42 nach Implantation MRT-Untersuchungen (T1, T2 und 3D CISS-Sequenzen) durchgef{\"u}hrt. Die Tumorvolumina wurden mit Hilfe dieser MRT-Untersuchungen ermittelt. Die histologische Aufarbeitung beinhaltete HE-, CD68-Makrophagen-, CD8-positive T Zellen- sowie Ki-67 Proliferations- F{\"a}rbungen in Paraffinschnitten von Gehirn, Tumor und Milz. In 15 der 20 behandelten Tiere entwickelten sich solide Tumoren. Am Tag 7 konnte lediglich bei zwei Tieren mittels MRT ein minimales Tumorwachstum nachgewiesen werden. In der Kontrollgruppe war bereits bei drei von neun Tieren minimales Tumorwachstum zu verzeichnen. Am Tag 14 zeigten sich bei 11 von 17 (65\%) Tieren der Versuchsgruppe solide Tumoren. Drei der verbleibenden 15 Tiere zeigten am Tag 21 erstmalig Tumorwachstum. Im Gegensatz dazu konnte in der Kontrollgruppe bereits an Tag 14 bei allen Tieren ein Tumorwachstum nachgewiesen werden. In der GM-CSF Gruppe entwickelten sich die Tumoren sp{\"a}ter und erreichten mit einem Median von 134mm³ ein geringeres Volumen als in der Kontrollgruppe (262mm³). Das mediane {\"U}berleben war mit 35 Tagen in der Gruppe der behandelten Tiere signifikant l{\"a}nger als in der Kontrollgruppe mit 24 Tagen. Zudem wurden in der histologischen Aufarbeitung der Tumoren signifikant mehr Makrophagen im Tumorgewebe nachgewiesen. Die Stimulation der Makrophagen durch GM CSF im orthotopen C6 Glioblastommodell der Ratte f{\"u}hrte zu einem beachtlich reduzierten und verz{\"o}gerten Tumorwachstum. Die behandelten Tiere {\"u}berlebten signifikant l{\"a}nger als die Tiere der Kontrollgruppe. Die aktuelle Datenlage best{\"a}tigt die bedeutende Rolle der angeborenen Immunabwehr durch Makrophagen in der Kontrolle des Tumorwachstums bei experimentellen Glioblastomen. Die Aktivierung der Makrophagen hatte einen deutlichen Einfluss auf das Tumorwachstum, wohingegen eine T Zell-Depletion nur einen geringen Einfluss darauf hatte. Makrophagen als Vertreter des angeborenen Immunsystems wurden bisher in ihrer Rolle der Tumorkontrolle untersch{\"a}tzt. Es bedarf noch weiterer Untersuchungen, ob die Makrophagen in Zukunft, ohne die k{\"o}rpereigenen Zellen anzugreifen, zur wirkungsvollen Tumorbek{\"a}mpfung herangezogen werden k{\"o}nnten.},
  subject      = {Glioblastoma multiforme},
  language  = {de}
}
@phdthesis{Karama2021,
  author    = {Karama, Alphonse},
  title     = {East African Seasonal Rainfall prediction using multiple linear regression and regression with ARIMA errors models},
  doi       = {10.25972/OPUS-25183},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-251831},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2021},
  abstract  = {The detrimental impacts of climate variability on water, agriculture, and food resources in East Africa underscore the importance of reliable seasonal climate prediction. To overcome this difficulty RARIMAE method were evolved. Applications RARIMAE in the literature shows that amalgamating different methods can be an efficient and effective way to improve the forecasts of time series under consideration. With these motivations, attempt have been made to develop a multiple linear regression model (MLR) and a RARIMAE models for forecasting seasonal rainfall in east Africa under the following objectives: 1. To develop MLR model for seasonal rainfall prediction in East Africa. 2. To develop a RARIMAE model for seasonal rainfall prediction in East Africa. 3. Comparison of model's efficiency under consideration In order to achieve the above objectives, the monthly precipitation data covering the period from 1949 to 2000 was obtained from Climate Research Unit (CRU). Next to that, the first differenced climate indices were used as predictors. In the first part of this study, the analyses of the rainfall fluctuation in whole Central- East Africa region which span over a longitude of 15 degrees East to 55 degrees East and a latitude of 15 degrees South to 15 degrees North was done by the help of maps. For models' comparison, the R-squared values for the MLR model are subtracted from the R-squared values of RARIMAE model. The results show positive values which indicates that R-squared is improved by RARIMAE model. On the other side, the root mean square errors (RMSE) values of the RARIMAE model are subtracted from the RMSE values of the MLR model and the results show negative value which indicates that RMSE is reduced by RARIMAE model for training and testing datasets. For the second part of this study, the area which is considered covers a longitude of 31.5 degrees East to 41 degrees East and a latitude of 3.5 degrees South to 0.5 degrees South. This region covers Central-East of the Democratic Republic of Congo (DRC), north of Burundi, south of Uganda, Rwanda, north of Tanzania and south of Kenya. Considering a model constructed based on the average rainfall time series in this region, the long rainfall season counts the nine months lead of the first principal component of Indian sea level pressure (SLP_PC19) and the nine months lead of Dipole Mode Index (DMI_LR9) as selected predictors for both statistical and predictive model. On the other side, the short rainfall season counts the three months lead of the first principal component of Indian sea surface temperature (SST_PC13) and the three months lead of Southern Oscillation Index (SOI_SR3) as predictors for predictive model. For short rainfall season statistical model SAOD current time series (SAOD_SR0) was added on the two predictors in predictive model. By applying a MLR model it is shown that the forecast can explain 27.4\% of the total variation and has a RMSE of 74.2mm/season for long rainfall season while for the RARIMAE the forecast explains 53.6\% of the total variation and has a RMSE of 59.4mm/season. By applying a MLR model it is shown that the forecast can explain 22.8\% of the total variation and has a RMSE of 106.1 mm/season for short rainfall season predictive model while for the RARIMAE the forecast explains 55.1\% of the total variation and has a RMSE of 81.1 mm/season. From such comparison, a significant rise in R-squared, a decrease of RMSE values were observed in RARIMAE models for both short rainfall and long rainfall season averaged time series. In terms of reliability, RARIMAE outperformed its MLR counterparts with better efficiency and accuracy. Therefore, whenever the data suffer from autocorrelation, we can go for MLR with ARIMA error, the ARIMA error part is more to correct the autocorrelation thereby improving the variance and productiveness of the model.},
  subject      = {Regression},
  language  = {en}
}