The world’s continuously increasing population leads to environmental challenges, among which, the urban heat island effect has been recognized as one of the leading environmental issues recently. Using traditional weather station (usually one or two within one city and placed in rural area) to monitor and model the canopy layer urban heat phenomenon does not provide enough spatial resolution. Alternatively, the Netatmo weather station, a low cost and citizen science weather sensor, is able to collect crowdsourced temperature records and has significant strength in spatial and temporal resolution in temperature measurement. Thanks to the variety of uses of the Netatmo weather station and its open API, more temperature data could be used for UHI research. However, for scientific use, the main challenge is the data quality. For one thing, the stations’ locations are set by users and are thus not accurate enough for temperature modeling in a complex city environment. For another, sensors some time generate unreliable records when exposed to solar radiance directly. These two things are actually highly interactional. Knowing the accurate location of stations could be helpful to calculate when the stations are exposed sun then filter outliers, and vice versa. However, the location information could be used to improve its accuracy is quite limited. Thus, the current work is focusing on develop an approach to determine the likely correct location of the stations. For the development of the relocation method, different spatial and sensor datasets have been used. The temperature data in the Hague in May, 2018 have been collected from Netatmo weather stations. Additionally, the AHN3 points cloud for solar simulation and BGT shapefile for creating new location have been investigated. The methodology of relocation process is divided into 6 steps: Sensor data pre-processing, Detecting higher temperature time, Generating potential location of stations, Computing sky view (dome) and solar parameter, Finding the most likely horizontal location of the station, and Assigning height value to points. These steps also have been used with another period time in the Hague for validation and one sample Netatmo sensor experiment in Delft will be conducted. The results proved the feasibility and rationality of the adopted methodology. Around 67% stations (new location) is shown more than 0.5 similarity when comparing with their solar simulation. Validation result detained by two period comparison indicates that over 70% Netatmo stations’ new location show high quality on both the horizontal and vertical dimensions after applying the process. Validation experiment is shown a real example of fluctuated air temperature and how it will be influenced by solar radiance. In the experiment, the location error is reduced from 16 meters to 4 meters, which proves that the methodology adopted by the project is helpful to improve the station’s location accuracy.

Bathymetric depth for shallow water regions is essential for coastal management and research. The measurements using echo sounding and LiDAR leave data gaps because vessels cannot reach nearshore waters or the green laser unable to penetrate specific areas. Satellite-Derived Bathymetry (SDB) is an alternative to extract shallow water depths that is able to overcome these problems using multispectral imagery. There are two approaches of SDB: analytical and empirical. The analytical method requires several water properties, which might not be known. The empirical method relies on the linear relationship between reflectances and depths, but the relationship may not be entirely linear due to bottom types variation, water column, and noise. Machine learning approaches have been used to address nonlinearity, but it treats pixels independently, whereas there is a spatial correlation that influences SDB computations since adjacent pixels are correlated to depth. This characteristic of the local connectivity can be captured by Convolution Neural Networks (CNN). Therefore, this thesis conducts a study of SDB using CNN. This research focuses on the following questions: (i) what kind of preprocessing is needed for the data sets; (ii) what kind of CNN architecture can be used; (iii) what is the accuracy of the method; and (iv) to what extent the pretrained model in certain areas can be reused in other areas. In order to represent a variety of depth, bottom type, turbidity, and water column properties, this study chooses six areas of interest in three different coastal regions: Puerto Rico, Key West, and Hawaii. With several CNN configurations, the optimum accuracy is obtained using three convolutional layers, a window size of 9x9, and the RGBNSS bands. Based on the experiment and comparison to the previous studies, the accuracy of SDB using the CNN approach outperforms the linear transform, the ratio transform, Random Forest, and the radiative transfer model. The results show that the accuracy decreases as the depth increases and in more turbid water. Comparison between different image preprocessing indicates another benefit of CNN: removing the need to preprocess images since suitable corrections can be automatically performed by CNN given adequate training. The use of multi-temporal images enhances the variety of training data and thus improves SDB accuracy. However, data variation should be equally distributed to avoid abnormality in the result. Transfer model analysis indicates several limitations of SDB results at particular depths or when implemented to a different water condition, making the coastal water characteristics considered when reusing a pretrained model from one area to another. In summary, CNN does not require additional image preprocessing and features specifications for training. CNN can produce better SDB accuracy than several other methods. The accuracy improves by increasing the variety of training data. However, SDB using the transfer model still need to be further investigated. A thorough identification of the proportion of sample data is needed to obtain balanced training data. In this way, it is more likely to produce a more reliable and more stable CNN model for extracting shallow water depths in the new data.