Water Quality Monitoring Dataset for Tilapia (Oreochromis niloticus) Aquaculture in Montería, Colombia (2024)

This dataset contains comprehensive water quality measurements for a tilapia (Oreochromis niloticus) aquaculture pond located in Montería, Colombia, collected over a six-month period in 2024. The dataset is part of a study aimed at enhancing water quality management in aquaculture systems, particularly in rural environments with limited technological infrastructure.

Data Collection and Parameters: The data was gathered through an Internet of Things (IoT) system designed to continuously monitor key water quality parameters. Parameters include:

Temperature (°C): Essential for maintaining optimal conditions for fish metabolism and growth.
Dissolved Oxygen (DO) (mg/L): Crucial for fish respiration and overall pond health.
pH: Indicates the acidity or alkalinity of the water, which affects fish health and nutrient availability.
Turbidity (NTU): Reflects the clarity of the water, which can impact light penetration and fish behavior.

Purpose and Applications: This dataset supports predictive modeling for water quality management using Machine Learning (ML) algorithms, including Random Forest and Support Vector Machines (SVM), with optimizations implemented via the Quantum Approximate Optimization Algorithm (QAOA). The dataset was utilized to train and validate models for real-time water quality prediction, achieving high accuracy in managing aquaculture conditions and reducing fish mortality.

Significance: The dataset provides valuable insights into water quality dynamics in tropical aquaculture settings, making it suitable for researchers, aquaculture managers, and data scientists focused on sustainable aquaculture practices. The data can aid in developing predictive models to stabilize water quality, support rural and urban aquaculture management, and contribute to global food security initiatives.

Acknowledgments: The collection of this dataset was made possible by an IoT-based monitoring system tailored for the environmental conditions of Montería, with an emphasis on adaptability for resource-limited rural regions.

本数据集囊括了位于哥伦比亚蒙特里亚的罗氏鲈（Oreochromis niloticus）养殖池塘的全面水质测量数据，该数据收集于2024年为期六个月的期间。该数据集是旨在提升水产养殖系统水质管理水平的科研项目的一部分，特别是针对技术基础设施有限的乡村环境。数据收集与参数：数据通过一个专为持续监测关键水质参数而设计的物联网（IoT）系统收集。参数包括：

温度（°C）：对维持鱼类新陈代谢和生长的优化条件至关重要。

溶解氧（DO）（mg/L）：对鱼类呼吸和池塘整体健康至关重要。

pH值：指示水的酸碱度，影响鱼类健康和营养物质的可用性。

浑浊度（NTU）：反映水的清晰度，可影响光穿透度和鱼类行为。

目的与应用：此数据集支持使用机器学习（ML）算法（包括随机森林和支持向量机SVM）进行水质管理的预测建模，通过量子近似优化算法（QAOA）进行优化。该数据集被用于训练和验证实时水质预测模型，实现了高精度管理水产养殖条件，降低了鱼类死亡率。

重要性：该数据集为热带水产养殖环境中水质动态提供了宝贵见解，适合研究工作者、水产养殖管理人员和数据科学家关注可持续水产养殖实践使用。数据有助于开发预测模型以稳定水质，支持城乡水产养殖管理，并为全球粮食安全倡议作出贡献。

致谢：本数据集的收集得益于一个针对蒙特里亚环境条件量身定制的基于物联网的监测系统，该系统着重于适应资源有限的乡村地区。