The accurate and detailed measurement of the vertical temperature, humidity, pressure, and wind profiles of the atmosphere is pivotal for high-resolution numerical weather prediction, the determination of atmospheric stability, as well as investigation of small-scale phenomena such as urban heat islands. Traditional approaches, such as weather balloons, have been indispensable but are constrained by cost, environmental impact, and data sparsity. In this article, we investigate uncrewed aerial systems (UASs) as an innovative platform for in situ atmospheric probing. By comparing data from a drone-mounted semiconductor temperature sensor (TMP117) with traditional radiosonde measurements, we spotlight the UAS-collected atmospheric data’s accuracy and such system suitability for atmospheric surface layer measurement. Our research encountered challenges linked with the inherent delays in achieving ambient temperature readings. However, by applying specific data processing techniques, including smoothing methodologies like the Savitzky–Golay filter, iterative smoothing, time shift, and Newton’s law of cooling, we have improved the data accuracy and consistency. In this article, 28 flights were examined and certain patterns between different methodologies and sensors were observed. Temperature differentials were assessed over a range of 100 m. The article highlights a notable accuracy achievement of 0.16 ± 0.014 °C with 95% confidence when applying Newton’s law of cooling in comparison to a radiosonde RS41’s data. Our findings demonstrate the potential of UASs in capturing accurate high-resolution vertical temperature profiles. This work posits that UASs, with further refinements, could revolutionize atmospheric data collection.

Maritime search-and-rescue (SAR) work typically involves scanning large sea areas looking for ships and related objects, where targets are sparse and appearance can be unknown. This labor- and capital-intensive task could be automated using reconnaissance drones and applying computer vision algorithms. In this work, the authors suggest the possibility of detecting man-made objects in marine backgrounds without prior knowledge of their appearance. The basis of detection is visual patterns (shapes), typical for such objects. Two algorithms were developed for this task: a deep learning fusion-based neural network consisting of a convolutional edge filter, an autoencoder, and a neural network (ANN), and a classical region-based detector built on Canny edges and geometric trimming. We curate a balanced dataset of 37,032 images (18,516 positive; 18,516 negative) derived from ships, platforms, and wind turbines and perform six-fold grouped cross-validation. The F1 score achieved by the artificial neural network-based method was no lower than 0.97, while 0.67 was scored by the region-based method. The result of the artificial neural network using a convolutional edge filter and a convolutional autoencoder was greater than those achieved by networks without such layers. The region-based method demonstrated an exceptional processing speed of 143 FPS. An algorithm involving both methods was proposed to be used for search and rescue operations using a drone. Results indicate that emphasizing shape primitives improves robustness to wave texture and reflections, limitations remain for very small targets. The experiment confirms the viability of using a shape-based method to detect objects characterized by distinct patterns in marine environments.