Bing Ouyang

Monitoring seaweed growth rates and biomass is crucial for optimizing harvest strategies in aquaculture systems. While such a task can be managed manually on a small farm with a few seaweed tanks, it is not feasible on a commercial farm with 1000s of tanks. To this end, an Internet of Things (IoT) based seaweed growth monitoring system is being developed at Harbor Branch Oceanographic Institute (HBOI) at Florida Atlantic University (FAU). Using the Integrated Multi-Trophic Aquaculture (IMTA) system at HBOI as the test site, the project aims to develop a solution that allows farm managers to monitor seaweed growth remotely using automated sensors. An important component of this IoT solution is the machine learning-based prediction model. This study introduces an advanced Long Short-Term Memory (LSTM)-based approach for forecasting seaweed growth and biomass. In particular, an algae growth mathematical model driven by readily available environmental and aquaculture conditions has been integrated as a physical constraint in the LSTM model. This design addresses a principal challenge in this study—the lack of continuous ground truth measurements, as the biomass is recorded only at discrete intervals (e.g., initial, weekly partial harvests, and final harvest). The LSTM models are trained and evaluated for their predictive performance using experimental and synthetic data. Compared with the LSTM models with MSE loss function alone, the results showed that the model with a loss function under physics constraint achieved a significantly lower error in predicting seaweed growth. The rationale behind choosing LSTM over other state-of-the-art models is presented in the paper. This study highlights the potential of integrating machine learning with physical models to optimize seaweed cultivation and support sustainable aquaculture practices. The proposed methodology can seamlessly extend to the remote sensing data in other aquaculture settings.

Monitoring seaweed growth rates and biomass is crucial for optimizing harvest strategies in aquaculture systems. While such a task can be performed manually on a small farm, such as the Integrated Multi-Trophic Aquaculture (IMTA) system at Harbor Branch Oceanographic Institute at Florida Atlantic University (HBOI), a commercial farm will have to rely on the automated sensor to perform such a task. This study introduces an advanced LSTM-based approach for forecasting seaweed growth and biomass. Utilizing a combination of real and synthetic data, LSTM models are trained and evaluated for their predictive performance. Synthetic sensor data was generated using mathematical equations that simulate realistic aquaculture conditions, with added noise to reflect sensor variability. Building on the foundation of the Pseudorandom Encoded Light for Evaluating Biomass (PEEB) sensor deployed at the seaweed tank in the HBOI IMTA system, we refine the process of biomass estimation by introducing non-linear regression models for predicting seaweed growth and biomass. The results showed that the LSTM model trained with a loss function under physics constraint, combining MSE and physical laws, outperformed models trained with MSE alone, achieving a significantly lower error in predicting seaweed growth. The variation trend of the predicted biomass from the network matched well with the sensor measurement after moving average preprocessing, demonstrating the robustness of the proposed technique in handling noisy sensor data. This study highlights the potential of integrating machine learning with physical models to optimize seaweed cultivation and support sustainable aquaculture practices.

We advanced the practical development of compressive hyperspectral cameras for remote sensing scenarios with a design that simultaneously compresses and captures high-quality spectral information of a scene via configurable measurements. We built a prototype imaging system that is compatible with light-modulation devices that encode the incoming spectrum. The sensing approach enables a substantial reduction in the volume of data collected and transmitted, facilitating large-scale remote hyperspectral imaging. A main advantage of our sensing design is that it allows for adaptive sampling. When prior information of a survey region is available or gained, the modulation patterns can be re-programmed to efficiently sample and detect desired endmembers. Given target spectral signatures, we propose an optimization scheme that guides the encoding process. The approach severely reduces the number of required sampling patterns, with the ability to achieve image segmentation and correct distortions. Additionally, to decode the modulated data, we considered a novel reconstruction algorithm suited for large-scale images. The computational methodology leverages the multidimensional structure and redundant representation of hyperspectral images via the canonical polyadic decomposition of multiway arrays. Under realistic remote sensing scenarios, we demonstrated the efficiency of our approach with several data sets collected by our prototype camera and reconstructed by our low-rank tensor decoder.

Marine food chains are highly stressed by aggressive fishing practices and environmental damage. Aquaculture has increasingly become a source of seafood which spares the deleterious impact on wild fisheries. However, continually monitoring water quality to successfully grow and harvest fish is labor intensive. The Hybrid Aerial Underwater Robotic System (HAUCS) is an Internet of Things (IoT) framework for aquaculture farms to relieve the farm operators of one of the most labor-intensive and time-consuming farm operations: water quality monitoring. To this end, HAUCS employs a swarm of unmanned aerial vehicles (UAVs) or drones integrated with underwater measurement devices to collect the in situ water quality data from aquaculture ponds. A critical aspect in HAUCS is to develop an effective path planning algorithm to be able to sample all the ponds on the farm with minimal resources (i.e., the number of UAVs and the power consumption of each UAV). Three methods of path planning for the UAVs are tested, a Graph Attention Model (GAM), the Google Linear Optimization Package (GLOP) and our proposed solution, the HAUCS Path Planning Algorithm (HPP). The designs of these path planning algorithms are discussed, and a simulator is developed to evaluate these methods’ performance. The algorithms are also experimentally validated at Southern Illinois University’s Aquaculture Research Center to demonstrate the feasibility of HAUCS. Based on the simulations and experimental studies, HPP is particularly suited for large farms, while GLOP or GAM is more suited to small or medium-sized farms.

Imaging through degraded visual environments is a challenging task in remote sensing missions. Image degradation may come from the loss of contrast due to particle scattering and/or distortion due to turbulence-induced effects. The problem is especially challenging when imaging from moving platforms such as autonomous underwater vehicles. One potential approach to address these issues is to use multiple images and employ a multi-frame image fusion technique to aid in the recovery of corrupted image detail and quality. A machine learning (ML)-based image enhancement and fusion technique is investigated to restore images distorted by underwater turbulence. The main contributions include the incorporation of a ML-based image weight predictor to predict the ideal weight maps to be used in an image fusion process. This network is trained using a generative adversarial network framework and a synthetically generated image dataset, which is created according to an analytical image degradation model. In addition, the image loss function for the weight map predictor is determined by the final fused image, resulting in a balanced fusion technique that can reduce image distortion, recover crisp image detail, and reduce the overall noise figure. Another key contribution of this paper is the adoption of an image loss function that incorporates an innovative combined correntropy and Fourier space loss function to reinforce the network in both the spatial and frequency domain. The performance of the proposed algorithm is evaluated using a synthetic validation dataset of images and several real datasets captured at the Naval Research Lab’s Simulated Turbulence and Turbidity Environment under various controlled turbulence intensities.

This article presents the experimental study of a biomass sensor to monitor the growth of macroalgae (seaweeds) in the Integrated Multi-Trophic Aquaculture (IMTA) at Harbor Branch Oceanographic Institute at Florida Atlantic University. Pseudorandom Encoded-light for Evaluating Biomass (PEEB) utilizes the measurements from a sequence of encoded light flashes to quantify the seaweed biomass. Such configuration ensures the sensor provides robust automated data acquisition under different ambient conditions and biomass densities. This data will be used to support a machine learning-based prediction biomass model, critical in any commercial-scale IMTA farm. A PEEB sensor based on an improved design has been developed based on an earlier feasibility study. The design of such a system and the initial tests at the macroalgal seaweed cultivation raceway in the HBOI IMTA system are discussed.

While robotics have been widely used in many agricultural practices such as harvesting, seeding, cattle monitoring, etc., aquaculture farming is an important, fast-growing sector of agriculture that has not seen significant adoption of advanced technologies such as robotics and the Internet of Things (IoT). In particular, dissolved oxygen (DO) monitoring, a practice in pond aquaculture essential to the health of the fish crops, remains labor-intensive and time-consuming. The Hybrid Aerial Underwater robotiCs System (HAUCS) is an IoT framework that aims to bring transformative changes to pond aquaculture. This paper focuses on the latest development in the HAUCS mobile sensing platform and field deployment. To address some shortcomings with the current implementation, the development of a novel rigid Kirigami-based robotic extension subsystem that can expand the functionality of the HAUCS platform is also being discussed.

This paper discusses the design and initial testing of a novel hydrophone array system dubbed the Underwater Inflatable Co-prime Sonar Array (UICSA). The UICSA will be a crucial component of an underwater deployable sensing network that can be rapidly deployed using compact autonomous underwater vehicles (AUVs). The UICSA initially is packed in a compact container to fit the payload space of an AUV. After deployment, the UICSA expands to its predetermined full length to acquire sensing data for source localization. More specifically, the mechanical compression of the UICSA is achieved through a non-rigid array support structure, which consists of flexible inflatable segments between adjoining hydrophones that are folded in order to package the UICSA for deployment. The system exploits compression in hydrophone layouts by utilizing a sparse array configuration, namely the co-prime array since it requires fewer hydrophones than a uniform linear array of the same length to estimate a given number of sources. With two-way compression, the storage, handling, and transportation of the compactly designed UICSA is convenient, particularly for the AUVs with limited payload space. The deployment concept and process are discussed, as well as the various UICSA designs of different support structures are described. A comparison of the various mechanical designs is presented and a novel hybrid-based expansion prototype is documented in detail. Laboratory study results of the UICSA prototype are presented that include water-swollen material tests in a pressurized environment and water tank validation of the inflation process. The UICSA prototype also has been deployed in the Harbor Branch channel to validate the performance, the related field test details and source localization results.

Robust underwater imaging sensors are essential in applications such as identifying and classifying marine animals in turbid waters, typically found around coastal monitoring sites. The Unobtrusive Multi-static Serial LiDAR Imager (UMSLI) has been developed to capture images taken in degraded underwater environments and provides superior range and image contrast over conventional optical cameras. In contrast to traditional underwater LiDAR systems that employ blue-green lasers, UMLSI will not harm the vision of marine animals, which is an important aspect in such settings. As with any other underwater LiDAR sensors, improving the quality of images taken in highly turbid water is essential to the UMSLI system. This paper proposes a novel machine learning image enhancement technique based on a Generative Adversarial Network (GAN) framework. One main contribution of the method is the incorporation of a correntropy-based perceptual loss. This technique has shown to be effective in enhancing ground-based images and has been adapted for LiDAR image enhancement. Given the limitation of existing underwater LiDAR data, a method for simulating degraded data for training is also presented. This LiDAR technique was validated using LiDAR data captured by the UMSLI system within Florida Atlantic University’s Harbor Branch Oceanographic Institute (FAU-HBOI) optical test facility and at the Marine and Coastal Research Laboratory at the Pacific Northwest National Laboratory (MCRL-PNNL). This image enhancement technique can be readily extended to other underwater LiDAR systems.