Solcellspaneler har fått ökad uppmärksamhet som en betydande källa till förnybar energi på grund av den ökande medvetenheten om klimatförändringar och behovet av hållbara energilösningar. I Sverige har detta lett till en kraftig ökning av solcellsanläggningar. I och med ökningen av solcellspaneler i urbana miljöer, har behovet av att kartlägga och inventera dessa anläggningar växt. Framsteg inom artificiell intelligens (AI) och bildanalys har öppnat möjligheter för automatiserade metoder som effektivt kan identifiera och segmentera solcellspaneler. Syftet med detta arbete är att utforska potentialen hos traditionella AI-modeller, som Support Vector Machines (SVM) och Random Forest (RF), samt faltningsnätverk av typen U-net, för att identifiera och segmentera solcellspaneler i svenska flygfotodata. Vidare undersöks i arbetet hur dessa modeller reagerar på reducerad datamängd samt vad för sorts features som höjer de traditionella modellernas prestanda i syfte att inventera solcellspaneler. Under arbetet skapas ett dataset om 2268, 1152 RGBI-data, där solcellspaneler utgör 22,8 procent av pixlarna. Data är hämtad från Lantmäteriet och har en spatial upplösning på 0.16m/pixel. Tre modeller implementeras och jämförs under olika förhållanden. Flertalet features utvunna från datasetet presenteras och förändringar av prestanda vid träning med dessa features mäts. För en utvärdering av modellernas precision tränas de först på 70% av det totala datasetet och utvärderas på de resterande 30%. En andra utvärdering utförs med reducerad datamängd där 35% av den totala datamängden används för träning och 30% för utvärdering. Prestandamätningar utförs på samma dataset för alla modeller där traditionella modeller tränas på RGB, RGBI, RGBI+features. U-net-modellen tränas på RGB-data. Resultaten visar att U-net-modellen presterar bäst i syfte att segmentera solcellspaneler med en F1-score på 0.91 och MCC på 0.89. Näst bäst är RF med en F1-score på 0.81 samt MCC på 0.76. Vid halvering av mängd träningsdata observeras störst negativ förändring av prestation på U-net-modellen, medan de traditionella modellerna syns påverkas mindre. Rätt urval av features observeras markant höja prestationen hos de traditionella modellerna. Sammanfattningsvis påvisar resultaten att neurala nätverk presterar bättre än traditionella modeller vid inventering av svenska solcellspaneler och betonar samtidigt vikten av rätt feature selection hos traditionella maskininlärningsmodeller. / Solar panels have gained increased attention as a significant source of renewable energy due to the growing awareness of climate change and the need for sustainable energy solutions. In Sweden, this has led to a rise in solar installations. With the increase of solar panels in urban areas, the need for accurate mapping and inventory of these installations has grown. Advances in artificial intelligence (AI) and image analysis have opened possibilities for automated methods for high precision identification av segmentation of solar panels. These automated methods reduce time consumption, resource use and the risk of human error. The aim of this work is to explore the potential of traditional AI models such as Support Vector Machines (SVM) and Random Forest (RF), as well as convolutional neural networks with the U-net architecture, to identify and segment solar panels in Swedish aerial imagery. Furthermore, the study investigates how these models perform with reduced data quantities. The study also examines which types of features enhance the performance of traditional models for the purpose of inventorying solar panels. During the study, a dataset of 2268, 1152 RGBI data was created, where solar panels constitute 22.8 percent of the pixels. This data, sourced from Lantmäteriet, has a spatial resolution of 0.16m/pixel. Three models were implemented and compared under various conditions. Multiple features extracted from the dataset were presented and performance changes during training with these features were measured. For evaluation the models were first trained on 70% of the total dataset and evaluated on the remaining 30%. A second evaluation was conducted with reduced data, using 35% for training and 30% for evaluation. Performance measurements were carried out on the same dataset for all models, where the traditional models were trained on RGB, RGBI, and RGBI + features, while the U-net model was trained on RGB data. In evaluation the U-net model achieved the highest performance in solar panel segmentation with an F1-score of 0.91 and an MCC of 0.89, followed by RF with an F1-score of 0.81 and an MCC of 0.76. Halving the training data resulted in a bigger impact on U-net's performance than on the traditional models. Optimal feature selection substantially improved traditional models, doubling SVM's F1-score when trained with additional features. In summary, the results indicate that neural networks perform better than traditional models in inventorying Swedish solar panels and emphasize the importance of correct feature selection in traditional machine learning models.

Image classification in Machine Learning encompasses the task of identification of objects in an image. The technique has applications in various areas such as e-commerce, social media and security surveillance. In this report the author explores the impact of using t-Distributed Stochastic Neighbor Embedding (t-SNE) on data as a preprocessing step when classifying multiple classes of clothing with a state-of-the-art Deep Convolutional Neural Network (DCNN). The t-SNE algorithm uses dimensionality reduction and groups similar objects close to each other in three-dimensional space. Extracting this information in the form of a positional coordinate gives us a new parameter which could help with the classification process since the features it uses can be different from that of the DCNN. Therefore, three slightly different DCNN models receives different input and are compared. The first benchmark model only receives pixel values, the second and third receive pixel values together with the positional coordinates from the t-SNE preprocessing for each data point, but with different hyperparameter values in the preprocessing step. The Fashion-MNIST dataset used contains 10 different clothing classes which are normalized and gray-scaled for easeof-use. The dataset contains 70.000 images in total. Results show minimum change in classification accuracy in the case of using a low-density map with higher learning rate as the data size increases, while a more dense map and lower learning rate performs a significant increase in accuracy of 4.4% when using a small data set. This is evidence for the fact that the method can be used to boost results when data is limited. / Bildklassificering i maskinlärning innefattar uppgiften att identifiera objekt i en bild. Tekniken har applikationer inom olika områden så som e-handel, sociala medier och säkerhetsövervakning. I denna rapport undersöker författaren effekten av att användat-Distributed Stochastic Neighbour Embedding (t-SNE) på data som ett förbehandlingssteg vid klassificering av flera klasser av kläder med ett state-of-the-art Deep Convolutio-nal Neural Network (DCNN). t-SNE-algoritmen använder dimensioneringsreduktion och grupperar liknande objekt nära varandra i tredimensionellt utrymme. Att extrahera denna information i form av en positionskoordinat ger oss en ny parameter som kan hjälpa till med klassificeringsprocessen eftersom funktionerna som den använder kan skilja sig från DCNN-modelen. Tre olika DCNN-modeller får olika in-data och jämförs därefter. Den första referensmodellen mottar endast pixelvärden, det andra och det tredje motar pixelvärden tillsammans med positionskoordinaterna från t-SNE-förbehandlingen för varje datapunkt men med olika hyperparametervärden i förbehandlingssteget. I studien används Fashion-MNIST datasetet som innehåller 10 olika klädklasser som är normaliserade och gråskalade för enkel användning. Datasetet innehåller totalt 70.000 bilder. Resultaten visar minst förändring i klassificeringsnoggrannheten vid användning av en låg densitets karta med högre inlärningsgrad allt eftersom datastorleken ökar, medan en mer tät karta och lägre inlärningsgrad uppnår en signifikant ökad noggrannhet på 4.4% när man använder en liten datamängd. Detta är bevis på att metoden kan användas för att öka klassificeringsresultaten när datamängden är begränsad.

Current disaster response strategies are based on damage assessments carried out on the ground, which can be dangerous following a ä destructive event. Damage assessments can also be performed remotely using satellite imagery, but are usually carried out through visual interpretation, which can take a lot of time. This thesis explored a way of using artificial intelligence to automate remote damage assessment. We implemented a dual-task U-Net deep learning model, trained it with the xBD dataset for assessing building damage, and applied the model to pre- and post-event very high resolution satellite imagery of the February 6, 2023 earthquakes in Turkey. The results were compared to damage maps produced using a traditional object based method by calculating the F1 scores associated with the outputs of each method and ground truth data that we compiled. The study areas were parts of the two cities Kahramanmaraş and Antakya. The deep learning model almost only correctly identified undamaged buildings, achieving F1 scores of 0.95 during training as well as 0.93 and 0.83 in the damage assessments of Kahramanmaras and Antakya, respectively. For the other damage classes, the best result was the classification of destroyed buildings, both in training and in the study areas, with a F1-score of 0.45 in training and 0.16 in Kahramanmaraş. The deep learning model performed similarly to the object based method. Although the thesis did not yield good damage maps in the areas of interest, it had many limitations, and there is still a lot of potential for deep learning models to be useful in building damage assessment.

Convolutional artificial neural networks can be applied for image-based object classification to inform automated actions, such as handling of objects on a production line. The present thesis describes theoretical background for creating a classifier and explores the effects of introducing a set of relatively recent techniques to an existing ensemble of classifiers in use for an industrial sorting system.The findings indicate that it's important to use spatial variety dropout regularization for high resolution image inputs, and use an optimizer configuration with good convergence properties. The findings also demonstrate examples of ensemble classifiers being effectively consolidated into unified models using the distillation technique. An analogue arrangement with optimization against multiple output targets, incorporating additional information, showed accuracy gains comparable to ensembling. For use of the classifier on test data with statistics different than those of the dataset, results indicate that augmentation of the input data during classifier creation helps performance, but would, in the current case, likely need to be guided by information about the distribution shift to have sufficiently positive impact to enable a practical application. I suggest, for future development, updated architectures, automated hyperparameter search and leveraging the bountiful unlabeled data potentially available from production lines.