Data for: A Low-Complexity Machine Learning Nitrate Loss Predictive Model – Towards Proactive Farm Management in a Networked Catchment

With the advent of Wireless Sensor Networks, the ability to predict nutrient-rich discharges, using on-node prediction models, offers huge potential for enabling real-time water reuse and management within an agriculturally-dominated catchment Existing discharge models use multiple parameters and large historical data which are difficult to extract and this, coupled with constraints on network nodes (battery life, computing power, sensor availability etc.) makes it necessary to develop low-dimensional models. This paper investigates a data-driven model for predicting daily total oxidized nitrate (TON) fluxes, and reduces the number of model parameters used to 5 – a reduction of at least 50%. Trained on only a 12-month training data set derived from published measured data, results for the model generated using an M5 decision tree, giving an R2 of 0.92 and a relative root mean squared error (RRMSE) of 26%. 80% of the residuals for test data fall within +/-0.05 Kg ha-1day-1 error range, which is minimal, offering an improvement over results obtained by contemporary research.

随着无线传感网络的兴起，运用节点预测模型预测富含营养物质的排放，为在以农业为主导的流域内实现实时水资源再利用和管理提供了巨大的潜力。现有的排放模型采用多个参数和大量的历史数据，这些数据提取难度较大。此外，网络节点（如电池寿命、计算能力、传感器可用性等）的约束条件使得开发低维模型变得必要。本文研究了用于预测每日总氧化亚硝酸盐（TON）通量的数据驱动模型，并将模型参数的数量减少到5个，相较于之前至少减少了50%。该模型仅基于从已发表的测量数据中提取的12个月训练数据集进行训练，使用M5决策树生成的模型结果显示R²值为0.92，相对均方根误差（RRMSE）为26%。测试数据中的80%残差落在±0.05 Kg ha-1day-1的误差范围内，这一误差极小，相较于当代研究成果，显著提升了预测效果。