Change detection is a topic of great interest in remote sensing. A good similarity metric to compute the variations among the images is the key to high-quality change detection. However, most existing approaches rely on the fixed threshold values or the user-provided ground truth in order to be effective. The inability to deal with artificial objects such as clouds and shadows is a significant difficulty for many change-detection methods. We propose a new unsupervised change-detection framework to address those critical points. The notion of homogeneous regions is introduced together with a set of geometric operations and statistic-based criteria to characterize and distinguish formally the change and nonchange areas in a pair of remote sensing images. Moreover, a robust and statistically well-posed family of stochastic distances is also proposed, which allows comparing the probability distributions of different regions/objects in the images. These stochastic measures are then used to train a support-vector-machine-based approach in order to detect the change/nonchange areas. Three study cases using the images acquired with different sensors are given in order to compare the proposed method with other well-known unsupervised methods.

Statement of Problem: Environmental engineering confronts complex challenges characterized by significant uncertainties. Traditional modeling methods often fail to effectively address these uncertainties. As a promising direction, this study explores fuzzy machine learning (ML) as an underutilized alternative. Research Question: Although the potential of fuzzy logic is widely acknowledged, can its capabilities truly enhance environmental engineering applications? Purpose: This research aims to deepen the understanding of the role and significance of fuzzy logic in managing uncertainty within environmental engineering applications. The objective is to contribute to both theoretical insights and practical implementations in this domain. Method: This research performs a systematic review carried out in alignment with PRISMA guidelines, encompassing 27 earlier studies that compare fuzzy ML with other methods across a variety of applications within the field of environmental engineering. Results: The findings demonstrate how fuzzy-based models consistently outperform traditional methods in scenarios marked by uncertainty. The originality of this research lies in its systematic comparison and the identification of fuzzy logic’s transparent, interpretable nature as particularly suited for environmental engineering challenges. This approach provides a new perspective on integrating fuzzy logic into environmental engineering, emphasizing its capability to offer more adaptable and resilient solutions. Conclusions: The analysis reveals that fuzzy-based models significantly excel in managing uncertainty compared to other methods. However, the study advocates for a case-by-case evaluation rather than a blanket replacement of traditional methods with fuzzy models. This approach encourages optimal selection based on specific project needs. Practical Implications: Our findings offer actionable insights for researchers and engineers, highlighting the transparent and interpretable nature of fuzzy models, along with their superior ability to handle uncertainties. Such attributes position fuzzy logic as a promising alternative in environmental engineering applications. Moreover, policymakers can leverage the reliability of fuzzy logic in developing ML-aided sustainable policies, thereby enhancing decision-making processes in environmental management.

Mental health benefits have been linked to human interaction with nature. However, most studies have been carried out in developed countries, limiting the generalizability of empirical findings to other parts of the world. To address this gap, this study was conducted in Brazil. The objective of the study was to assess whether the frequency of contact with nature affects the occurrence of anxiety, stress, and depression. Data were collected between June and July 2022 through an online survey (n = 1186, 1 − α = 0.95, p = 0.05, 1 − β = 0.85, rho = 0.1). Thus, the public online survey made it possible to carry out voluntary response sampling suitable for an exploratory study, with the purpose of an initial understanding of an under-researched population. First, a logistic regression was performed for quantifying the association between contact with nature and mental symptoms. In addition, three groups of people having different frequencies (low, medium, and high) of contact with nature and a reference group, comprised of those who reported no contact, were compared using Kruskal–Wallis and Dwass–Steel–Chritchlow–Fligner tests. This study employs a cross-sectional design and relies on retrospective recall. As a result, the research hypothesis was confirmed. People who very rarely have contact with nature had a 97.95% probability of moderate occurrence of stress, which decreases to 20.98% for people who have contact with nature frequently. Furthermore, in the same comparison, the probability of occurrence was 3.6 times lower for anxiety and 4.8 times lower for depression. In conclusion, the evidence indicates that the greater the frequency of contact with nature, the lower the occurrence of stress, anxiety, and depression symptoms. Nevertheless, the benefits of this contact were significant only when its frequency was moderate (about once or twice a week) or higher.

Algal blooms are a frequent subject in scientific discussions and are the focus of many recent studies, mainly due to their adverse effect on society. Given the lack of ground truth data and the need to develop tools for their detection and monitoring, this research proposes a novel method to automate detection. Concepts derived from multi-temporal image series processing, spectral indices and classification with One-class Support Vector Machine (OC-SVM) are used in this proposal. Imagery from multi-spectral sensors on Landsat-8 and MODIS were acquired through the Google Earth Engine API (GEE API). In order to evaluate our method, two bloom detection case studies (Lake Erie (USA) and Lake Taihu (China)) were performed. Comparisons were made with methods based on spectral index thresholds. Also, to demonstrate the performance of the OC-SVM classifier compared to other machine learning methods, the proposal was adapted to be used with a Random Forest (RF) classifier, having its results added to the analysis. In situ measurements show that the proposed method delivers highly accurate results compared to spectral index thresholding approaches. However, a drawback of the proposal refers to its higher computational cost. The application of the new method to a real-world bloom case is demonstrated.

Coagulation is the most sensitive step in drinking water treatment. Underdosing may not yield the required water quality, whereas overdosing may result in higher costs and excess sludge. Traditionally, the coagulant dosage is set based on bath experiments performed manually, known as jar tests. Therefore, this test does not allow real-time dosing control, and its accuracy is subject to operator experience. Alternatively, solutions based on machine learning (ML) have been evaluated as computer-aided alternatives. Despite these advances, there is open debate on the most suitable ML method applied to the coagulation process, capable of the most highly accurate prediction. This study addresses this gap, where a comparative analysis between ML methods was performed. As a research hypothesis, a data-driven (D²) fuzzy inference system (FIS) should provide the best performance due to its ability to deal with uncertainties inherent to complex processes. Although ML methods have been widely investigated, only a few studies report hybrid neuro-fuzzy systems applied to coagulation. Thus, to the best of our knowledge, this is the first study thus far to address the accuracy of this non-hybrid data-driven FIS (D²FIS) for such an application. The D²FIS provided the smallest error (0.69 mg/L), overcoming the adaptive neuro-fuzzy inference system (1.09), cascade-correlation network (1.18), gene expression programming (1.15), polynomial neural network (1.20), probabilistic network (1.17), random forest (1.26), radial basis function network (1.28), stochastic gradient tree boost (1.25), and support vector machine (1.17). This finding points to the D²FIS as a promising alternative tool for accurate real-time coagulant dosage in drinking water treatment. In conclusion, the D²FIS can help WTPs to reduce operating costs, prevent errors associated with manual processes and operator experience, and standardize the efficacy with real-time and highly accurate predictions, and enhance safety for the water industry. Moreover, the evidence from this study can assist in filling the gap with the most suitable ML method and identifying a promising alternative for computer-aided coagulant dosing. For further advances, future studies should address the potential of the D²FIS for the control and optimization of other unit operations in drinking water treatment.