Impact statement
This study provided a practical and affordable approach to monitoring water quality and aquatic biodiversity in Lagos Lagoon, one of Nigeria’s most ecologically and economically important aquatic systems. It addressed a pressing challenge faced by many developing nations on how to effectively track environmental changes in aquatic ecosystems without relying on costly or complex equipment. By designing, building and deploying a low-cost multi-sensor system, the study demonstrated how essential environmental data, such as temperature, underwater acoustics and visual imagery, could be collected continuously and reliably under real-world conditions. The system’s success showed that robust environmental monitoring is achievable even in resource-constrained settings. The sensor system proved adaptable for monitoring localized water conditions, enabling early detection of pollution and ecosystem disturbances. This information could help environmental managers and policymakers make timely and informed decisions to protect biodiversity, safeguard human health and guide sustainable development. Additionally, the study explored the use of artificial intelligence to assist in species identification, including potentially endangered aquatic organisms. This capability offered a new avenue for supporting conservation efforts through data-driven ecological assessments. Beyond research and policy implications, the system also presented opportunities for education and public engagement. It offered a hands-on, accessible tool for students, citizen scientists and local communities to participate in understanding and preserving their aquatic environments. In conclusion, the study went beyond technical innovation; it delivered a scalable, real-world solution for continuous environmental monitoring, with the potential to transform how aquatic ecosystems are managed in regions facing mounting ecological pressures and limited resources.
Introduction
Lagoons served as a transitional ecosystem between freshwater and marine environments, offering essential ecological services, such as water purification, climate regulation and habitat provision for a wide variety of aquatic organisms (Rodrigues-Filho et al., Reference Rodrigues-Filho, Macêdo, Sarmento, Pimenta, Alonso, Teixeira and Cionek2023; Singh et al., Reference Singh, Kumar, Kumar, Dwivedi, Singh, Mishra, Seth and Sharma2024). Lagos Lagoon, one of the largest coastal water bodies in West Africa, played a central role in Nigeria’s environmental and economic landscape (Davies-Vollum et al., Reference Davies-Vollum, Koomson and Raha2024). However, this lagoon had been increasingly affected by rapid urbanization, industrial effluents, solid waste accumulation and the impacts of climate variability (Apoko, Reference Apoko2014). These anthropogenic stressors contributed to the degradation of water quality and the loss of aquatic biodiversity, highlighting the urgent need for sustained ecological monitoring to inform conservation strategies and resource management policies (Ahmed et al., Reference Ahmed, Kumar, Kabir, Zuhara, Mehjabin, Tasannum and Mofijur2022). Conventional monitoring methods, such as manual water sampling and laboratory-based analyses, remained widely used in aquatic ecosystem assessment (Kianpoor Kalkhajeh et al., Reference Kianpoor Kalkhajeh, Jabbarian Amiri, Huang, Henareh Khalyani, Hu, Gao and Thompson2019). However, these approaches were often expensive, labor-intensive and limited in their ability to provide real-time or spatially comprehensive data (Mohanty et al., Reference Mohanty, Pandey, Srivastava, Srivastava, Mohanty, Pandey, Srivastava and Srivastava2025). Additionally, such methods frequently overlook subtle ecological changes, particularly those involving biological indicators that integrate environmental conditions over time. The high cost and logistical complexity of repeated field sampling further limited their practicality in developing regions with constrained resources (Marvin et al., Reference Marvin, Koh, Lynam, Wich, Davies, Krishnamurthy and Asner2016). Aquatic macroinvertebrates emerged as valuable bioindicators due to their varied tolerance levels to pollutants and their sensitivity to changes in environmental conditions (López-López and Sedeño-Díaz, Reference López-López, Sedeño-Díaz and Lopes2015). These organisms played crucial roles in aquatic food webs and ecosystem processes and responded to both short-term disturbances and long-term environmental trends. Their widespread distribution and differential pollution tolerance made them suitable for assessing ecological health across different water bodies. Unlike chemical measurements that captured only momentary conditions, macroinvertebrate communities reflected cumulative impacts, thereby offering a more comprehensive picture of ecosystem status (Singh et al., Reference Singh, Kumar, Kumar, Dwivedi, Singh, Mishra, Seth and Sharma2024). Emerging technologies presented new opportunities to overcome the limitations of traditional monitoring systems. Low-cost sensor networks, when combined with artificial intelligence (AI) and machine learning (ML) algorithms, allowed for the real-time acquisition, processing and analysis of environmental data at scale (Zainurin et al., Reference Zainurin, Wan Ismail, Mahamud, Ismail, Jamaludin, Ariffin and Wan Ahmad Kamil2022; Sharma et al., Reference Sharma, Sharma, Grover, Sharma, Sharma and Grover2024). These systems continuously monitored water quality parameters, such as temperature, salinity, turbidity, pH and dissolved oxygen, while AI-enabled components facilitated species recognition through acoustic and visual cues (Rycyk et al., Reference Rycyk, Bolaji, Factheu and Kamla Takoukam2022; Dogan et al., Reference Dogan, Vaidya, Bromhal and Banday2024). This integration enabled automated, high-resolution environmental assessments and offered a viable alternative for long-term ecological monitoring, particularly in regions with limited infrastructure and funding (Danovaro et al., Reference Danovaro, Carugati, Berzano, Cahill, Carvalho, Chenuil, Corinaldesi, Cristina, David, Dell’Anno, Dzhembekova, Garcés, Gasol, Goela, Féral, Ferrera, Forster, Kurekin, Rastelli, Marinova, Miller, Moncheva, Newton, Pearman, Pitois, Reñé, Rodríguez-Ezpeleta, Saggiomo, SGH, Stefanova, Wilson, Martire, Greco, SKJ, Mangoni and Borja2016; Datta et al., Reference Datta, Maharaj, Prabhu, Bhowmik, Marino, Akbari, Rupavatharam, Sujeetha, Anantrao, Poduvattil, Kumar and Kleczkowski2021). This study aimed to design, develop and field-deploy a cost-effective, AI-driven multi-sensor system for real-time aquatic ecosystem monitoring in Lagos Lagoon. By integrating low-cost sensing technologies with automated species detection and environmental parameter tracking, the research addressed fundamental gaps in aquatic biodiversity surveillance and water resource management. The deployment of such a system demonstrated the feasibility of using scalable and affordable technologies for environmental monitoring in developing countries. The outcomes of this study offered practical insights for improving conservation practices, supporting data-driven environmental policy and advancing sustainable management of aquatic ecosystems under increasing anthropogenic pressure.
Methodology
Hardware calibration and testing
The Raspberry Pi-based multi-sensor data logging system was designed following a structured approach that included hardware integration, software development, calibration and system validation. Figure 1 shows the system architecture and design. The hardware configuration comprised a Raspberry Pi 3 microcomputer connected to a DS18B20 temperature sensor, a microphone and a camera module.
System architecture and data flow diagram.
A 5 V power supply unit powered the system, and the Raspberry Pi’s General Purpose Input/output (GPIO) pins were configured to interface directly with the sensors (Vujović and Maksimović, Reference Vujović and Maksimović2014). The system’s architecture enabled real-time data acquisition, processing and storage, while also supporting remote access via a RealVNC server linked to an internet-connected remote viewer Vijay et al., Reference Vijay, Abishek, Sabarish and Krishnan2023). During assembly, all hardware components were mounted securely and configured to support synchronized environmental data collection. Python scripts were developed to automate sensor data reading, logging and storage in structured formats, such as Comma Separated Values (CSV). The RealVNC server setup allowed users to monitor data remotely and control the system in real time. Calibration of the DS18B20 temperature sensor was carried out under controlled laboratory conditions using a mercury-in-glass thermometer for reference. Figure 2 shows the data calibration of the temperature sensor. The sensor was mounted externally on the experimental water container to minimize thermal interference from the Raspberry Pi’s internal heat and to allow for rapid heat dissipation.
Data calibration for the temperature sensor.
The camera module was calibrated through adjustments in focus, white balance and exposure settings to ensure optimal image clarity across varying lighting conditions. The microphone was tuned using the Linux-based “arecord” tool to enhance underwater sound capture. To validate the system’s waterproofing and sensor functionality, submersion tests were conducted in two stages: initially in a 35 cm deep water tank, and subsequently in a 250-l drum at 1-m depth. These trials verified sensor durability, enclosure integrity and stable data acquisition under aquatic conditions. Observations from these tests informed iterative improvements in the waterproof casing design to ensure consistent sensor performance and data reliability during field deployments.
AI model training and validation
AI algorithms were developed to enable automated species identification in Lagos Lagoon by analyzing both visual and acoustic data. Hydrophones were deployed at multiple depths and locations within the lagoon to capture underwater soundscapes for acoustic monitoring (Lillis et al., Reference Lillis, Caruso, Mooney, Llopiz, Bohnenstiehl and Eggleston2018). Convolutional neural networks (CNNs) and recurrent neural networks were considered for classifying the captured audio signals based on known vocalizations of aquatic species. These ML models were trained using labeled datasets containing species-specific acoustic patterns (Datta et al., Reference Datta, Maharaj, Prabhu, Bhowmik, Marino, Akbari, Rupavatharam, Sujeetha, Anantrao, Poduvattil, Kumar and Kleczkowski2021) and were continuously refined through retraining and validation to improve classification accuracy and reduce false positives. In parallel, a deep learning model based on CNNs was implemented for image-based aquatic species identification. The visual dataset comprised 31 distinct species, which were partitioned into training (8,791 images), validation (2,751 images) and testing (1,760 images) subsets. To enhance model robustness and generalization, data augmentation techniques, such as rescaling, shearing, zooming and horizontal flipping, were applied. The CNN architecture featured four convolutional layers with increasing filter sizes (from 32 to 256), followed by batch normalization, max pooling and dropout layers to prevent overfitting. A global average pooling layer was incorporated to reduce spatial dimensions, feeding into fully connected dense layers with L2 regularization. The final output layer used softmax activation to support multi-class classification. The model was compiled with the Adam optimizer (learning rate = 0.001) and categorical cross-entropy as the loss function. Model performance was tracked using accuracy and loss metrics across epochs. Early stopping criteria and dynamic learning rate adjustments were applied to optimize training. The final model demonstrated the capability to recognize species based on visual and acoustic data, contributing significantly to biodiversity monitoring in dynamic aquatic environments.
System evaluation
The performance, reliability and practical deployment of the low-cost multi-sensor system were carried out in both laboratory and field settings. The evaluation focused on key operational parameters, including sensor drift, biofouling resistance, power efficiency and data transmission reliability over time (Chan et al., Reference Chan, Schillereff, Baas, Chadwick, Main, Mulligan and Thompson2021). Comparative assessments with commercial-grade sensors were also planned to benchmark the accuracy and feasibility of the low-cost alternatives. Additionally, stakeholder engagement with local researchers and environmental agencies was initiated to evaluate the system’s scalability and utility for long-term biodiversity monitoring. System integration tests were conducted to ensure interoperability among the temperature sensor, camera, microphone and Raspberry Pi-based data logging unit. Custom Python scripts were executed simultaneously across all components to verify real-time concurrent data acquisition. The system was networked and accessed remotely via a RealVNC server, demonstrating its capability for remote monitoring and control. Power efficiency was tested using a 22.2 kWh backup battery, which provided ~6 h of continuous operation. To evaluate environmental durability, staged submersion trials were conducted using a 250-l water drum at a depth of ~1 m. These trials confirmed the waterproof enclosure’s integrity and the system’s ability to record temperature, acoustic and visual data in submerged conditions. While real-time Wi-Fi data transmission failed beyond a 10 cm submersion depth due to signal attenuation, the system continued logging data locally, allowing for full retrieval upon resurfacing. The results of these evaluations validated the robustness and operational viability of the low-cost sensor system, confirming its suitability for extended deployment in dynamic aquatic environments, such as Lagos Lagoon.
Field deployment
The low-cost sensor system in (Figure 3a,b) was deployed on December 17–18, 2024, at Lagos Lagoon (6°30′27″N, 3°24′14″E) to collect real-time data on habitat conditions and aquatic biodiversity. Figure 4 illustrates the deployment process, highlighting both daytime and nighttime operations. The sensors were strategically installed at a fixed location to ensure consistent and reliable data collection. A stable power supply and reliable connectivity are required to facilitate continuous monitoring and data transmission. Before field deployment, the system underwent laboratory testing, where it successfully collected temperature data, images and audio recordings. To enhance durability in aquatic environments, the sensors were enclosed in a waterproof casing and initially tested in a controlled water tank (35 cm depth). During early trials, minor water ingress was observed, requiring three design iterations to achieve an effective waterproof seal. The moment the enclosure was fully sealed, further testing was conducted at a depth of 1 m using a 250 L water drum. The system maintained full functionality under these conditions, confirming its waterproofing effectiveness. However, a major limitation observed was in real-time data transmission. The Wi-Fi signal was lost after ~10 cm of submersion, consistent with known challenges in underwater wireless sensor networks, where signal attenuation and propagation delays hinder effective communication. Despite this limitation, all recorded data were stored locally within the Raspberry Pi, allowing for data retrieval upon resurfacing.
(a) Hardware system setup. (b) Complete system set up.
(a) Configuration of the system before deployment. (b)Deployment of sensors at the Lagoon water during the daytime. (c) Deployment of sensors in the Lagoon water during the night.
Results and discussion
Temperature measurement
The temperature variations recorded by the deployed sensor are presented in the graph, with temperature (°C) on the vertical axis and time on the horizontal axis. The temperature data were taken at 2-s intervals and converted to minutes’ average. The data indicate a gradual increase in temperature, peaking at ~31.36 °C around 08:05 PM, followed by a slight decline, as shown in Figure 5. These fluctuations may be attributed to environmental factors, such as solar heating, water movement or sensor positioning. This study highlights the transformative potential of AI-powered multi-sensor systems in environmental research. The device demonstrated reliability in temperature monitoring and organism detection, reinforcing its applicability for aquatic ecosystem studies. However, further refinements are necessary to enhance accuracy and adaptability across diverse aquatic conditions (Abdelwahab, Reference Abdelwahab2023).
Temperature recorded by the monitoring system.
Acoustic measurement
The acoustic measurements were collected at Lagos Lagoon, capturing underwater sound activity over time, as shown in Figure 6. The top graph is a spectrogram, which visualizes sound intensity across different frequencies. The horizontal axis represents time, while the vertical axis represents frequency (Hz). The color intensity denotes amplitude, where darker regions indicate lower sound levels, and brighter regions reflect stronger signals. The spectrogram reveals varying frequency distributions, likely influenced by aquatic life, boat traffic or environmental noise. The lower graph, the magnitude spectrum, highlights dominant frequency components, showing that most recorded acoustic energy is concentrated below 500 Hz. This suggests that the primary sound sources in the area covered by the lagoon operate within the low-frequency range, a characteristic commonly associated with both biological and anthropogenic underwater noise. These findings corroborate with Kershenbaum et al. (Reference Kershenbaum, Akçay, Babu-Saheer, Barnhill, Best, Cauzinille and Dunn2025), who reported that automatic detection of biological sounds enables faster and more efficient analysis of large acoustic datasets, a crucial advancement for processing long-duration field recordings. Furthermore, methods for localizing sound sources help minimize discrepancies in recordings, leading to more accurate identification and quantification of individual sound producers.
Sound wave spectrum recorded (top: amplitude spectrum, middle: frequency spectrum, and bottom: magnitude spectrum).
Visual data collection
Figure 7 presents sample images of organisms captured during the pilot field test. The device successfully documented aquatic vegetation, including water hyacinths. However, due to the brackish nature and high turbidity of the Lagos Lagoon, the images appeared dark, limiting visibility and detail. These findings emphasize the need for improved lighting or image enhancement techniques to enhance data quality in future deployments. Datta et al. (Reference Datta, Maharaj, Prabhu, Bhowmik, Marino, Akbari, Rupavatharam, Sujeetha, Anantrao, Poduvattil, Kumar and Kleczkowski2021) reported that the use of custom-built multispectral cameras, along with advanced data augmentation techniques, such as spectral transformations and synthetic data generation, can improve dataset diversity and account for complex environmental conditions. Integrating similar approaches could enhance image clarity and increase the accuracy of visual data analysis in challenging aquatic environments.
Dry stalk of water hyacinth (Eichhornia crassipes).
AI machine learning model deployment
In Table 1, we report the first 20 epochs of the training results for the CNN model with key performance metrics. The training and validation accuracy gradually increased but remained relatively low due to the complexity of the dataset. As shown in Figure 8, both training and validation loss exhibited a downward trend, suggesting the model was learning, albeit at a slow rate. The learning rate remained constant at 0.001 throughout the training. Figure 9 demonstrates that the ML model effectively captures images in line with the trend of the observed dataset, indicating a reasonable ability to generalize to unseen data. However, the noticeable deviations suggest that further optimization is required, such as deploying a more powerful graphics processing unit (GPU). This may include increasing the model’s complexity by adding additional layers or filters, applying data augmentation to improve the diversity of the training data and fine-tuning hyperparameters, such as the learning rate and dropout rate. After training, the AI model was deployed on a Raspberry Pi within a multi-sensor data logging system designed for species detection in aquatic ecosystems. If recognition failed, the image was stored without an event log. This process continued iteratively until the monitoring campaign concluded, ensuring continuous data collection and analysis in real-world conditions.
Training performance metrics over the last five epochs
Loss and validation loss for the image recognition machine learning model.
Machine learning model accuracy for image recognition.
Conclusion
This study was successfully designed, integrated and deployed with a low-cost multi-sensor system for environmental monitoring in Lagos Lagoon. The system effectively collected temperature, acoustic and visual data, offering valuable insights into aquatic conditions. Acoustic analysis identified dominant low-frequency sound sources, consistent with biological and anthropogenic noise patterns. However, visual data collection faced challenges due to high turbidity, emphasizing the need for image enhancement techniques. The AI-based species recognition model demonstrated potential but requires further optimization to improve accuracy and adaptability. While real-time data transmission was hindered by signal loss underwater, local data logging ensured comprehensive data collection for post-deployment analysis. Beyond its technical achievements, this study highlights the transformative potential of AI-powered multi-sensor systems in environmental research. The device exhibited reliability in temperature monitoring and organism detection, yet further refinements are necessary to enhance accuracy and adaptability across diverse aquatic conditions. Training deep learning models, particularly CNN, requires significant computational power, which benefits from extensive training over large datasets. The use of a more powerful GPU will enhance training efficiency by enabling faster computation of convolutions, batch normalization and backpropagation, thereby allowing for an increased number of training iterations, larger batch sizes and deeper architecture. Future efforts will focus on integrating advanced deep learning architectures, refining image processing techniques and expanding datasets to include a broader range of species and environmental conditions. These findings contribute to the growing body of research advocating for AI-driven ecological monitoring solutions, reinforcing their pivotal role in sustainable environmental management.
Open peer review
To view the open peer review materials for this article, please visit http://doi.org/10.1017/wat.2025.10006.
Data availability statement
The data supporting the findings of this study are available from the corresponding author upon request. Data include sensor output logs, acoustic recordings, image datasets and machine learning model outputs used in the environmental monitoring system.
Acknowledgments
The authors would like to thank the 2024 Research Grant under the Nigeria Artificial Intelligence Research (NAIR) Scheme NITDA/HQ/RG/AI6932787063 for funding this study.
Author contribution
Aneyo A.I. conceptualized and designed the study, supervised field deployment and contributed to the manuscript draft. Oladipo M.O. and Adebari F.A. led the development of the data logging system and contributed to the algorithm implementation. Doherty V.F. coordinated biological assessments and aquatic species identification protocols. Ehigie J.O. and Ikpele A.O. supported statistical analysis, model validation and data interpretation. Atoyebi A.O. facilitated environmental data collection and contributed to the literature review and manuscript editing. Balogun P.O. contributed to the integration and calibration of acoustic and imaging components and supported system testing during field trials. All authors contributed to data interpretation, critically reviewed the manuscript and approved the final version for publication.
Financial support
This research was supported by the 2024 Research Grant under the Nigeria Artificial Intelligence Research (NAIR) Scheme, administered by the National Information Technology Development Agency (NITDA), grant number NITDA/HQ/RG/AI6932787063.
Competing interests
The authors declare none.
Ethics statement
Ethical approval was not required for this study as it did not involve human participants or the handling of live animals beyond standard environmental sampling procedures.
Open access
Comments
Aneyo Idowu A. PhD
ianeyo@unilag.edu.ng
University of Lagos, Akoka,
Lagos, Nigeria
Postcode-101017
+234(0)8062745194
25th March, 2025
Editor-in-Chief
Cambridge Prisms: Water
Submission of Manuscript for Consideration in the the Cambridge Prisms: Water
Dear Editor,
We are pleased to submit our manuscript titled “Real-Time Monitoring of Water Quality Dynamics Using Low-Cost Sensor Networks in Lagos Lagoon” for consideration for publication in the Cambridge Prisms: Water. This study presents the development and deployment of a cost-effective, multi-sensor data logging system for real-time water quality monitoring in Lagos Lagoon, an important and environmentally vulnerable urban water body.
The research integrates temperature sensors, hydrophones, and imaging devices to collect environmental data, with the aim of providing an affordable and scalable alternative to traditional aquatic monitoring methods. By employing artificial intelligence (AI)-based species identification techniques, our study offers insights into biodiversity assessment and real-time environmental monitoring. The findings highlight key challenges and opportunities associated with the use of low-cost sensor networks, making a significant contribution to sustainable water resource management and conservation efforts.
We affirm that this manuscript is original, has not been published elsewhere, and is not under consideration by another journal. All authors have read and approved the manuscript and declare no conflicts of interest. Additionally, data supporting our findings are available upon request.
We appreciate your time and consideration and look forward to your feedback. Please do not hesitate to contact us should you require further information.
Sincerely,
Aneyo Idowu (PhD)