Advances in Remote Sensing Technology, Machine Learning and Deep Learning for Marine Oil Spill Detection, Prediction and Vulnerability Assessment

Prediction of the marine spreading of low sulfur fuel oil using the long short-term memory model trained with three-phase numerical simulations

In this study, we focus on the development and validation of a deep learning (long short-term memory, LSTM)-based algorithm to predict the accidental spreading of LSFO (low sulfur fuel oil) on the water surface. The data for the training was obtained by numerical simulations of artificial geometries with different configurations of islands and shorelines and wind speeds (2.0-8.0 m/s). For simulating the spread of oils in O(102) km scales, the volume of fluid and discrete phase models were adopted, and the kinematic variables of particle location, particle velocity, and water velocity were collected as input features for LSTM model. The predicted spreading pattern of LSFO matched well with the simulation (less than 10 % in terms of the mean absolute error for the untrained data). Finally, we applied the model to the Wakashio LSFO spill accident, considering actual geometry and weather information, which confirmed the practical feasibility of the present model.

The application of laser‑induced fluorescence in oil spill detection

Over the past two decades, oil spills have been one of the most serious ecological disasters, causing massive damage to the aquatic and terrestrial ecosystems as well as the socio-economy. In view of this situation, several methods have been developed and utilized to analyze oil samples. Among these methods, laser-induced fluorescence (LIF) technology has been widely used in oil spill detection due to its classification method, which is based on the fluorescence characteristics of chemical material in oil. This review systematically summarized the LIF technology from the perspective of excitation wavelength selection and the application of traditional and novel machine learning algorithms to fluorescence spectrum processing, both of which are critical for qualitative and quantitative analysis of oil spills. It can be seen that an appropriate excitation wavelength is indispensable for spectral discrimination due to different kinds of polycyclic aromatic hydrocarbons' (PAHs) compounds in petroleum products. By summarizing some articles related to LIF technology, we discuss the influence of the excitation wavelength on the accuracy of the oil spill detection model and proposed several suggestions on the selection of excitation wavelength. In addition, we introduced some traditional and novel machine learning (ML) algorithms and discussed the strengths and weaknesses of these algorithms and their applicable scenarios. With an appropriate excitation wavelength and data processing algorithm, it is believed that laser-induced fluorescence technology will become an efficient technique for real-time detection and analysis of oil spills.

Offshore Oil Spill Detection Based on CNN, DBSCAN, and Hyperspectral Imaging

Offshore oil spills have the potential to inflict substantial ecological damage, underscoring the critical importance of timely offshore oil spill detection and remediation. At present, offshore oil spill detection typically combines hyperspectral imaging with deep learning techniques. While these methodologies have made significant advancements, they prove inadequate in scenarios requiring real-time detection due to limited model detection speeds. To address this challenge, a method for detecting oil spill areas is introduced, combining convolutional neural networks (CNNs) with the DBSCAN clustering algorithm. This method aims to enhance the efficiency of oil spill area detection in real-time scenarios, providing a potential solution to the limitations posed by the intricate structures of existing models. The proposed method includes a pre-feature selection process applied to the spectral data, followed by pixel classification using a convolutional neural network (CNN) model. Subsequently, the DBSCAN algorithm is employed to segment oil spill areas from the classification results. To validate our proposed method, we simulate an offshore oil spill environment in the laboratory, utilizing a hyperspectral sensing device to collect data and create a dataset. We then compare our method with three other models-DRSNet, CNN-Visual Transformer, and GCN-conducting a comprehensive analysis to evaluate the advantages and limitations of each model.

Assessing potential of the Geostationary Littoral Imaging and Monitoring Radiometer (GLIMR) for water quality monitoring across the coastal United States

The Geostationary Littoral Imaging and Monitoring Radiometer (GLIMR) will provide unique high temporal frequency observations of the United States coastal waters to quantify processes that vary on short temporal and spatial scales. The frequency and coverage of observations from geostationary orbit will improve quantification and reduce uncertainty in tracking water quality events such as harmful algal blooms and oil spills. This study looks at the potential for GLIMR to complement existing satellite platforms from its unique geostationary viewpoint for water quality and oil spill monitoring with a focus on temporal and spatial resolution aspects. Water quality measures derived from satellite imagery, such as harmful algal blooms, thick oil, and oil emulsions are observable with glint <0.005 sr-1, while oil films require glint >10-5 sr-1. Daily imaging hours range from 6 to 12 h for water quality measures, and 0 to 6 h for oil film applications throughout the year as defined by sun glint strength. Spatial pixel resolution is 300 m at nadir and median pixel resolution was 391 m across the entire field of regard, with higher spatial resolution across all spectral bands in the Gulf of Mexico than existing satellites, such as MODIS and VIIRS, used for oil spill surveillance reports. The potential for beneficial glint use in oil film detection and quality flagging for other water quality parameters was greatest at lower latitudes and changed location throughout the day from the West and East Coasts of the United States. GLIMR scan times can change from the planned ocean color default of 0.763 s depending on the signal-to-noise ratio application requirement and can match existing and future satellite mission regions of interest to leverage multi-mission observations.

Hierarchical deep learning model to simulate phytoplankton at phylum/class and genus levels and zooplankton at the genus level

Harmful algal blooms (HABs) have become a global issue, affecting public health and water industries in numerous countries. Because funds for monitoring HABs are limited, model development may be an alternative approach for understanding and managing HABs. Continuous monitoring based on grab sampling is time-consuming, costly, and labor-intensive. However, improving simulation performance remains a major challenge in modeling, and current methods are limited to simulating phytoplankton (e.g., Microcystis sp., Anabaena sp., Aulacoseira sp., Cyclotella sp., Pediastrum sp., and Eudorina sp.) and zooplankton (e.g., Cyclotella sp., Pediastrum sp., and Eudorina sp.) at the genus level. The traditional modeling approach is limited for evaluating the interactions between phytoplankton and zooplankton. Recently, deep learning (DL) models have been proposed for solving modeling problems because of their large data handling capabilities and model structure flexibilities. In this study, we evaluated the applicability of DL for simulating phytoplankton at the phylum/class and genus levels and zooplankton at the genus level. Our work was an explicit representation of the taxonomic and ecological hierarchy of the DL model structure. The prerequisite for this model design was the data collection at two taxonomic and hierarchical levels. Our model consisted of hierarchical DL with classification transformer (TF) and regression TF models. These DL models were hierarchically connected; the output of the phylum/class level model was transferred to the genus level simulation model, and the output of the genus level model was fed into the zooplankton simulation model. The classification TF model determined the phytoplankton occurrence initiation date, whereas the regression TF model quantified the cell concentration of plankton. The hierarchical DL showed potential to simulate phytoplankton at the phylum/class and genus levels by producing average R^2, and root mean standard error values of 0.42 and 0.83 [log(cells mL^-1)], respectively. All simulated plankton results closely matched the measured concentrations. Particularly, the simulated cyanobacteria showed good agreement with the measured cell concentration, with an R² value of 0.72. In addition, our simulated result showed good agreement in peak concentration compared to observations. However, a limitation remained in following the temporal variation of Tintinnopsis sp. and Bosmia sp. Using an importance map from the TF model, water temperature, total phosphorus, and total nitrogen were identified as significant variables influencing phytoplankton and zooplankton blooms. Overall, our study demonstrated that DL can be used for modeling HABs at the phylum/class and genus levels.

Log Transformed Coherency Matrix for Differentiating Scattering Behaviour of Oil Spill Emulsions Using SAR Images

Oil spills on the ocean surface are a serious threat to the marine ecosystem. Automation of oil spill detection through full/dual polarimetric Synthetic Aperture Radar (SAR) images is considered a good aid for oil spill disaster management. This paper uses the power of log transformation to discern the scattering behavior more effectively from the coherency matrix (T3). The proposed coherency matrix is tested on patches of the clean sea surface and four different classes of oil spills, viz. heavy sedimented oil, thick oil, oil-water emulsion, fresh oil; by analyzing the entropy (H), anisotropy (A), and mean scattering angle alpha (α), following the H/A/α decomposition. Experimental results show that not only does the proposed T3 matrix differentiate between Bragg scattering of the clean sea surface from a random scattering of thick oil spills but is also able to distinguish between different emulsions of oil spills with water and sediments. Moreover, unlike classical T3, the proposed method distinguishes concrete-like structures and heavy sedimented oil even though both exhibit similar scattering behavior. The proposed algorithm is developed and validated on the data acquired by the UAVSAR full polarimetric L band SAR sensor over the Gulf of Mexico (GOM) region during the Deepwater Horizon (DWH) oil spill accident in June 2010.

The Use of Machine Learning Algorithms in Urban Tree Species Classification

Trees are the key components of urban vegetation in cities. The timely and accurate identification of existing urban tree species with their location is the most important task for improving air, water, and land quality; reducing carbon accumulation; mitigating urban heat island effects; and protecting soil and water balance. Light detection and ranging (LiDAR) is frequently used for extracting high-resolution structural information regarding tree objects. LiDAR systems are a cost-effective alternative to the traditional ways of identifying tree species, such as field surveys and aerial photograph interpretation. The aim of this work was to assess the usage of machine learning algorithms for classifying the deciduous (broadleaf) and coniferous tree species from 3D raw LiDAR data on the Davutpasa Campus of Yildiz Technical University, Istanbul, Turkey. First, ground, building, and low, medium, and high vegetation classes were acquired from raw LiDAR data using a hierarchical-rule-based classification method. Next, individual tree crowns were segmented using a mean shift clustering algorithm from high vegetation points. A total of 25 spatial- and intensity-based features were utilized for support vector machine (SVM), random forest (RF), and multi-layer perceptron (MLP) classifiers to discriminate deciduous and coniferous tree species in the urban area. The machine learning-based classification’s overall accuracies were 80%, 83.75%, and 73.75% for the SVM, RF, and MLP classifiers, respectively, in split 70/30 (training/testing). The SVM and RF algorithms generally gave better classification results than the MLP algorithm for identifying the urban tree species.

Decision Fusion of Deep Learning and Shallow Learning for Marine Oil Spill Detection

Marine oil spills are an emergency of great harm and have become a hot topic in marine environmental monitoring research. Optical remote sensing is an important means to monitor marine oil spills. Clouds, weather, and light control the amount of available data, which often limit feature characterization using a single classifier and therefore difficult to accurate monitoring of marine oil spills. In this paper, we develop a decision fusion algorithm to integrate deep learning methods and shallow learning methods based on multi-scale features for improving oil spill detection accuracy in the case of limited samples. Based on the multi-scale features after wavelet transform, two deep learning methods and two classical shallow learning algorithms are used to extract oil slick information from hyperspectral oil spill images. The decision fusion algorithm based on fuzzy membership degree is introduced to fuse multi-source oil spill information. The research shows that oil spill detection accuracy using the decision fusion algorithm is higher than that of the single detection algorithms. It is worth noting that oil spill detection accuracy is affected by different scale features. The decision fusion algorithm under the first-level scale features can further improve the accuracy of oil spill detection. The overall classification accuracy of the proposed method is 91.93%, which is 2.03%, 2.15%, 1.32%, and 0.43% higher than that of SVM, DBN, 1D-CNN, and MRF-CNN algorithms, respectively.

Determine the Land-Use Land-Cover Changes, Urban Expansion and Their Driving Factors for Sustainable Development in Gazipur Bangladesh

At present, urbanization is a very common phenomenon around the world, especially in developing countries, and has a significant impact on the land-use/land-cover of specific areas, producing some unwanted effects. Bangladesh is a tightly inhabited country whose urban population is increasing every day due to the expansion of infrastructure and industry. This study explores the land-use/land-cover change detection and urban dynamics of Gazipur district, Bangladesh, a newly developed industrial hub and city corporation, by using satellite imagery covering every 10-year interval over the period from 1990 to 2020. Supervised classification with a maximum likelihood classifier was used to gather spatial and temporal information from Landsat 5 (TM), 7 (ETM+) and 8 (OLI/TIRS) images. The Geographical Information System (GIS) methodology was also employed to detect changes over time. The kappa coefficient ranged between 0.75 and 0.90. The agricultural land was observed to be shrinking very rapidly, with an area of 716 km2 in 2020. Urbanization increased rapidly in this area, and the urban area grew by more than 500% during the study period. The urbanized area expanded along major roads such as the Dhaka–Mymensingh Highway and Dhaka bypass road. The urbanized area was, moreover, concentrated near the boundary line of Dhaka, the capital city of Bangladesh. Urban expansion was found to be influenced by demographic-, economic-, location- and accessibility-related factors. Therefore, similarly to many countries, concrete urban and development policies should be formulated to preserve the environment and, thereby, achieve sustainable development goal (SDG) 11 (sustainable cities and communities).

Advances in IoT and Smart Sensors for Remote Sensing and Agriculture Applications

Modern sensors find their wide usage in a variety of applications such as robotics, navigation, automation, remote sensing, underwater imaging, etc. and in recent years the sensors with advanced techniques such as the artificial intelligence (AI) play a significant role in the field of remote sensing and smart agriculture. The AI enabled sensors work as smart sensors and additionally the advent of the Internet of Things (IoT) has resulted into very useful tools in the field of agriculture by making available different types of sensor-based equipment and devices. In this paper, we have focused on an extensive study of the advances in smart sensors and IoT, employed in remote sensing and agriculture applications such as the assessment of weather conditions and soil quality; the crop monitoring; the use of robots for harvesting and weeding; the employment of drones. The emphasis has been given to specific types of sensors and sensor technologies by presenting an extensive study, review, comparison and recommendation for advancements in IoT that would help researchers, agriculturists, remote sensing scientists and policy makers in their research and implementations.

On-site marine oil spillage monitoring probes formed by fixing oxygen sensors into hydrophobic/oleophilic porous materials for early-stage spotty pollution warning

The oil spillage monitoring probe is developed by oxygen consumption sensor and hydrophobic/oleophilic porous materials. The oils could be monitored when they absorbed into the pores of the material to deplete the oxygen level inside the material.