Huma Zia

Predicting discharge using a low complexity machine learning model

Enabling real time water quality management using collaborative networked farms.Discharge predictive model uses 3 simple field parameters and 12-month training data.M5 tree based proposed model, trained on real data, give R2 as 0.82 and RRMSE a 35.9%.80% of the residuals for the predicted values fall within ?2mm discharge depth/day error range.The proposed model gives comparable results when compared to contemporary research. This paper reports on the validation of a simplified discharge prediction model that is suitable for implementation on a resourced constrained system such as a wireless sensor network, which will allow their operation to become more proactive rather than reactive. The data-driven model, utilising an M5 decision tree modelling technique, is validated using a 12-month training data set derived from published measured data. Daily runoff and drainage is predicted, and the results are compared with existing data-driven models developed in this domain. Results for the model give an R2 of 0.82 and Root Relative Mean Square Error (RRMSE) of 35.9%. 80% of the residuals for the predicted test values fall within a ?2mm discharge depth/day error range. The main significance is that the proposed model gives comparable results with fewer samples and simpler parameters when compared to previous published research, which offers the potential for implementation in resource constrained monitoring and control systems.

How could sensor networks help with agricultural water management issues? Optimizing irrigation scheduling through networked soil-moisture sensors

Irrigated agriculture provides 40% of the Worlds food from 20% of the agricultural land but uses 70% of all global freshwater withdrawals. However, even supposedly efficient and well-managed irrigation systems waste up to 50% of the water applied to the crops under them. Meeting the food needs of an increasing world population from a static or even decreasing land base will, therefore require improved efficiencies in irrigated agriculture and better use of these finite water resources. The first part of this paper reports on a field-based research project which examined a suite of conventional and alternative irrigation systems which were installed at a farm in south west Australia and assessed and compared in terms of their Water Use Efficiency. All “alternative” systems outperformed the conventional surface (flood) irrigation systems with comparative water savings of around 50%. The second part of the paper assesses the potential Water Use Efficiency improvements at farm and system-scales which could be achieved through linking these irrigation systems to wireless soil-moisture sensor networks which are being developed by the authors and which are reported in detail in associate papers. Improving irrigation scheduling and management by better (and, where appropriate, automatic) links to near real-time soil moisture data is shown to produce water savings of up to 30 GL per year at the irrigation system scale.

An Objective Based Classification of Aggregation Techniques for Wireless Sensor Networks

Wireless Sensor Networks have gained immense popularity in recent years due to their ever increasing capabilities and wide range of critical applications. A huge body of research efforts has been dedicated to find ways to utilize limited resources of these sensor nodes in an efficient manner. One of the common ways to minimize energy consumption has been aggregation of input data. We note that every aggregation technique has an improvement objective to achieve with respect to the output it produces. Each technique is designed to achieve some target e.g. reduce data size, minimize transmission energy, enhance accuracy etc. This paper presents a comprehensive survey of aggregation techniques that can be used in distributed manner to improve lifetime and energy conservation of wireless sensor networks. Main contribution of this work is proposal of a novel classification of such techniques based on the type of improvement they offer when applied to WSNs. Due to the existence of a myriad of definitions of aggregation, we first review the meaning of term aggregation that can be applied to WSN. The concept is then associated with the proposed classes. Each class of techniques is divided into a number of subclasses and a brief literature review of related work in WSN for each of these is also presented.

Data-driven low-complexity nitrate loss model utilizing sensor information — Towards collaborative farm management with wireless sensor networks

Excessive or poorly timed application of irrigation and fertilizers, coupled with the inherent inefficiency of nutrient uptake by crops result in nutrient fluxes into the water system. The ability to predict nutrient-rich discharges, in real time, can be very valuable to enable reuse mechanisms within farm systems. Wireless Sensor Networks (WSNs) offer an opportunity to monitor environmental systems with unprecedented temporal and spatial resolution. As part of our previous work, we proposed a novel framework (WQMCM) to combine increasingly common local farm-scale sensor networks across a catchment to learn and predict (using predictive models) the impact of catchment events on their downstream environments, allowing dynamic decision. Existing models use complex parameters which are difficult to extract and this, coupled with constraints on network nodes (battery life, computing power etc., availability of sensors) makes it necessary to develop simplified models for deployment within the networks. The paper investigates data-driven model for predicting daily total oxidized nitrate (TON) fluxes by seeking simplification in model parameters and using only a yearlong training data set. Data from a catchment in Ireland is used for training the model. Model simplification is investigated by abstracting details from an existing nitrate loss model. By using M5 decision tree model on the training samples of the proposed parameters, results give R2 as 0.92 and RRMSE as 0.26. The proposed novel model gives better results with fewer samples and simple parameters when compared to the traditional model. This shows promise for enabling real time nutrient control and management within the collaborative networked farm system.