Agricultural Decision Support Systems Research Articles

Effect of a participatory approach on the successful development of agricultural decision support systems: The case of Pigs2win

This paper explores how a decision support system (DSS) can be developed that complies with the critical success factors of such systems. A participatory approach is used to develop Pigs2win, a DSS for Flemish pig farms. Pigs2win uses frontier analysis for comparative farm analysis. The participatory approach influences the selection of stakeholders, objective setting and evaluation of Pigs2win. Outcomes of the participatory approach result in features of Pigs2win that positively influence its compliance with critical success factors. Based on our experience with Pigs2win, we put forward points that need attention when a participatory approach is organized.

Distributed Resource Allocation

The growth of technological capabilities of mobile devices, the evolution of wireless communication technologies, and the maturity of embedded systems contributed to expand the Machine to machine (M2M) concept. M2M refers to data communication between machines without human intervention. The objective of this paper is to present the grand schemes of a model to be used in an agricultural Decision support System. The authors start by explaining and justifying the need for a hybrid system that uses both Multi-Agent System (MAS) and Constraint Programming (CP) paradigms. Then, the authors propose an approach for Constraint Programming and Multi-Agent System mixing based on controller agent concept. The authors present concrete constraints and agents to be used in a distributed architecture based on the proposed approach for M2M services and agricultural decision support. The platform is built in Java using general interfaces of both MAS and Constraint Satisfaction Problem (CSP) platforms and the conception is made by agent UML (AUML).

Rainwater Management Model Development for Agriculture in the Savu Island Semi-Arid Region

Savu Island is a semiarid region with few rainfalls. The meager annual rainfall of about 1,000-1,500 mm that lasts for three to five months tends to cause draught. To cope with this situation, the Author tries to develop a rainwater management model located in Daieko village. This model constitutes an infrastructure that consists of check dam series which are constructed by simulating a computerized model of decision supporting system called “Rainwater Management for Agriculture Decision Support System (RMA-DSS) model” in the research location of Daieko village. Employing a simulated RMA-DSS model; the locations for check-dam series, and dug-wells can be determined, the size of potential irrigable lands can be determined based on water balance analysis of water samples taken from simulated check dams and inundated lands. Through this model the sufficiency of water supply for agricultural purposes and the land size for cultivation area can be predicted with a high degree of certainty.

Dynamic Real Time Distributed Sensor Network Based Database Management System Using XML, JAVA and PHP Technologies

Wireless Sensor Network (WSN) is well known for distributed real time systems for various applications. In order to handle the increasing functionality and complexity of high resolution spatio-temporal sensory database, there is a strong need for a system/tool to analyse real time data associated with distributed sensor network systems. There are a few package/systems available to maintain the near real time database system/management, which are expensive and requires expertise. Hence, there is a need for a cost effective and easy to use dynamic real-time data repository system to provide real time data (raw as well as usable units) in a structured format. In the present study, a distributed sensor network system, with Agrisens (AS) and FieldServer (FS) as well as FS-based Flux Tower and FieldTwitter, is used, which consists of network of sensors and field images to observe/collect the real time weather, crop and environmental parameters for precision agriculture. The real time FieldServer-based spatio-temporal high resolution dynamic sensory data was converted into Dynamic Real-Time Database Management System (DRTDBMS) in a structured format for both raw and converted (with usable units) data. A web interface has been developed to access the DRTDBMS and exclusive domain has been created with the help of open/free Information and Communication Technology (ICT) tools in Extendable Markup Language (XML) using (Hypertext preprocessor) PHP algorithms and with eXtensible Hyper Text Markup Language (XHTML) self-scripting. The proposed DRTDBMS prototype, called GeoSense DRTDBMS, which is a part of the ongoing IndoJapan initiative ‘ICT and Sensor Network based Decision Support Systems in Agriculture and Environment Assessment’, will be integrated with GeoSense cloud server to provide database (dynamic real-time weather/soil/crop and environmental parameters) and modeling services (crop water requirement and simulated rice yield modeling). GeoSense-cloud server has been developed with Opera-Unite for file sharing, web server (with cost effective web server tools Windows Apache MySQL PHP-WAMP and X -any operating systems Apache MySQL PHP and Perl –XAMPP), file upload, and web proxy functionalities. Currently, the GeoSense DRTDBMS is useful to the rural farming community for ubiquitous decision making in precision agriculture aspects. In future, this DRTDBMS system could be used in climate/environmental systems to understand the micro-climatic variations in real-time mode.

Networks of practice for co-construction of agricultural decision support systems: Case studies of precision dairy farms in Australia

The on-farm use of commercial decision support systems (DSSs) presents learning and adaptation challenges for farmers and their social learning networks. A study of six Australian dairy farms installing new precision dairy farming technology was undertaken to develop an in-depth picture of the issues occurring at the interface where precision farming data and decision-making meet. A qualitative exploratory case study method was used, with farmers each interviewed up to five times from pre-installation until 2years of use. A three-phase learning trajectory was observed amongst farmers involving early learning, consolidation, and advanced use. Farmers exhibited experiential learning but also learned via interaction with a network of on- and off-farm contacts forming a network of practice around the new users. This precision dairy farming network of practice formed a vital method of exchanging knowledge on how to best use technology and data in farming systems, with DSSs acting as a boundary object for learning. Externalisation of tacit knowledge into an explicit form suitable for DSSs was a major focus of this social learning. Co-construction of DSS knowledge in the emerging network was impeded by the absence of potentially important agents, in addition to the incomplete links between existing agents such as technology retailers and farmers. A technological innovation systems perspective is used to propose an improved framework to make greater use of translators and intermediaries. It is aimed at improving links amongst the community to more effectively aid farmers in creating new knowledge in agricultural DSS use.

Primary Study on Building Water-Saving AgriculturalDecision Support System Based on GIS

This paper built a system integrating data input and output, management, analysis and decision, and supported by GIS and Decision Support System technologies, and specilized water-saving model, and combined the state of agricultural water consumption in the Ganzhou district, Zhangye. This system offset the limits of traditional agricultural water-saving models on data analysis and expression, and greatly enhanced the functions of agricultural water-saving DSS. By analyzing the system demand, this paper proposed the framework of agricultural water-saving DSS, and designed the main functions of the system.

Model Development of Rainwater Management for Agriculture Decision Support System in Semi Arid Area

Land cultivation for agricultural purposes in semiarid area is usually carried out only once a year specifically during the rainy season. The condition is even worse since it is not without the risk of failure because of dry-spell or water-logging. To cope with this situation, the researchers developed a model of Rainwater Management for Agriculture Decision Supporting System (RMA-DSS). The objective of this RMA-DSS is to facilitate the decision making to build water infrastructure. Using this program it is hoped that sufficient water supply for specific crops with correct planting time can be guaranteed, which in turn will optimize harvest. The model consists of three parts, namely, rainfall-runoff-infiltration model, crop water requirement-irrigation-drainage model and rainwater management for agriculture model. The Models are designed using Microsoft Excel’s Macro Visual Basic and finalized with Visual Basic language program for operating spatial database of map object and non spatial database.

A Meteorological Data Service System and its Application

Meteorological conditions play an important role in agricultural practice and agricultural DSS usually takes weather data as a critical data source. A meteorological data service system was designed and implemented to provide better performance for Chinese users. Based on the service system, a web application providing online weather data retrieval and downloading was also developed. The service system was practically used in a decision support system for eucalypt management, and proved to be very feasible as an online weather data source for agricultural decision support system. Base on this service system, it is expected that agricultural researchers and decision support systems can easily obtain weather data and further improve their agricultural decision making process.

Agricultural decision support systems facilitating co-learning: a case study on environmental impacts of sugarcane production

Decision support systems (DSSs) are one of the ways in which agricultural scientists have attempted to make agricultural systems science more accessible to farmers and to foster innovation. Recently, there has been a shift towards more participatory processes in development and application of DSSs to enhance their end-user use. Apart from increasing adoption, these participatory processes are also likely to enhance co-learning resulting from development/application of DSSs. Learning is a valuable process in increasing sustainability of natural resource management, so the application of DSSs in a learning context can make a contribution to the global challenges faced by agriculture. We developed a framework, using concepts drawn from social studies of science and technology, describing the phases of the participatory DSS development/application process and its likely outcomes. We analysed experiences of participants in a case study exploring more sustainable management of nitrogen fertilizer in sugarcane production in an environmentally sensitive area of northeastern Australia. The data illustrate theoretical constructs underpinning the framework and learning processes within the case study. The framework and case study results demonstrate the value of participatory DSS development/application as a co-learning process, an outcome not traditionally valued by agricultural DSS developers and one that is likely to help address the challenges faced by agricultural sustainability.

The Theory and Method of Agricultural Expert Decision Support System

The Theory and Method of Agricultural Expert Decision Support System

Emerging consensus on desirable characteristics of tools to support farmers’ management of climate risk in Australia

The prospect that decision support systems (DSS) can help farmers adjust their management to suit seasonal conditions by putting scientific knowledge and rational risk management algorithms at farmers’ fingertips continues to challenge the science and extension community. A number of reviews of agricultural DSS have called for a re-appraisal of the field and for the need to reflect on past mistakes and to learn from social and management theory. The objective of this paper was to investigate whether there is an emerging consensus, among stakeholders in DSS for Australian agriculture, about the lessons learned from past experience with DSS tools. This investigation was conducted in three parts. The first part was a distillation of suggestions for best practice from the relevant literature. The second part was a reflection on what the champions of five current DSS development and delivery efforts in Australia learned from their recent efforts. The third part tested the level of support for the combined findings from the first and second approaches by surveying 23 stakeholders in the research, development, delivery and funding of DSS. The key propositions relating to best practice that were supported by the survey, listed according to the strength of support, were: 1. It is essential to have a plan for delivery of the DSS beyond the initial funding period. 2. DSS need to be embedded in a support network consisting of farmers, consultants and researchers. 3. DSS development requires the commitment of a critical mass of appropriately skilled people. 4. A DSS should aim to educate farmers’ intuition rather than replace it with optimised recommendations. 5. A DSS should enable users to experiment with options that satisfy their needs rather than attempt to present ‘optimised’ solutions. 6. DSS tools stand on the quality and authority of their underlying science and require ongoing improvement, testing and validation. 7. DSS development should not commence unless it is backed by marketing information and a plan for delivery of the DSS beyond the initial funding period. While the DSS stakeholders supported the proposition that it is essential to have a plan for delivery of a DSS beyond the funding period, the majority resisted the notion of DSS development being market-driven and especially commercial delivery of DSS. We argue that since public funding of the delivery of DSS for farmers’ management of climate risk is highly unlikely, reaping the benefits of lessons learned from past efforts will require that DSS stakeholders change their perception of the commercial delivery model or find an alternative way to fund the delivery of DSS beyond the R&D phase.

A conceptual framework for guiding the participatory development of agricultural decision support systems

Scientists develop decision support systems (DSSs) to make agricultural science more accessible for farmers and extension officers. Despite the growing use of participatory approaches in agricultural DSS development, reflection on this endeavour has largely focused on the ‘doing’ of participation or the ‘problem of implementation’ when DSSs have not been adopted by stakeholders. There has been little reference to relevant theoretical approaches to the social processes involved in ‘participation’ or ‘implementation’. However, if DSS use is to reach its full potential, a more conceptually informed understanding of how stakeholders collaborate in the participatory development of DSSs is required. To contribute to this conceptualisation, we developed a framework based on three concepts drawn from the field of science and technology studies: technological frames, interpretative flexibility and boundary objects. The framework highlights the importance and value of social learning for participatory DSS development, which relies upon exploring the participating parties’ different perspectives on the agricultural system represented in the DSS. Our framework provides a broad definition of success for participatory DSS development, placing greater weight on learning during the participatory process compared with subsequent use of the DSS by farmers and/or advisors. Two case studies of stakeholder collaboration to develop an irrigation scheduling DSS for sugarcane production were used to explore the relevance of the framework. The concepts in the framework were clearly displayed during the case studies. At the conclusion of the studies there were contrasting outcomes for the DSS. One group of farmers was keen to apply it in their ongoing irrigation management, while another saw little relative advantage in use of the DSS. In both instances co-learning occurred amongst case study participants, so the participatory process was clearly a success.

Monitoring Global Croplands with Coarse Resolution Earth Observations: The Global Agriculture Monitoring (GLAM) Project

In recent years there has been a dramatic increase in the demand for timely, comprehensive global agricultural intelligence. Timely information on global crop production is indispensable for combating the growing stress on the world’s crop production and for securing both short-term and long-term stable and reliable supply of food. Global agriculture monitoring systems are critical to providing this kind of intelligence and global earth observations are an essential component of an effective global agricultural monitoring system as they offer timely, objective, global information on croplands distribution, crop development and conditions as the growing season progresses. The Global Agriculture Monitoring Project (GLAM), a joint NASA, USDA, UMD and SDSU initiative, has built a global agricultural monitoring system that provides the USDA Foreign Agricultural Service (FAS) with timely, easily accessible, scientifically-validated remotely-sensed data and derived products as well as data analysis tools, for crop-condition monitoring and production assessment. This system is an integral component of the USDA’s FAS Decision Support System (DSS) for agriculture. It has significantly improved the FAS crop analysts’ ability to monitor crop conditions, and to quantitatively forecast crop yields through the provision of timely, high-quality global earth observations data in a format customized for FAS alongside a suite of data analysis tools. FAS crop analysts use these satellite data in a ‘convergence of evidence’ approach with meteorological data, field reports, crop models, attaché reports and local reports. The USDA FAS is currently the only operational provider of timely, objective crop production forecasts at the global scale. These forecasts are routinely used by the other US Federal government agencies as well as by commodity trading companies, farmers, relief agencies and foreign governments. This paper discusses the operational components and new developments of the GLAM monitoring system as well as the future role of earth observations in global agricultural monitoring.

Effects of June winds on rainfall in the coastal region of Kenya

Although the equatorial Eastern region of Africa is adjacent to the Indian Ocean, it tends to exhibit a drier climate rather than one characterized by abundant tropical rains. A number of studies on rainfall variability in the East African region have tended to suggest a stronger influence of local factors in controlling rainfall amounts and their characteristics rather than the global wind circulation system. A climatic phenomenon that is locally termed “June winds” is unique to East Africa’s coastal region. The study mainly involved analysing rainfall anomalies and means of 39- year meteorological data from the region and data from earlier studies about the region. The results indicate that June winds occur annually after the onset of long rains between the months of May and June. They impart subsidence, drying and cloud free conditions, altering the climatological properties in the areas they traverse. The attainment of peak June wind velocities causes a characteristic depression in rainfall probability and amounts on their course, similar to the ‘Ganges depression’ of temperatures in the Indian subcontinent, which in turn affects available soil moisture for crop growth. The results also reveal existence of years of “above-normal rains” (herein referred to as El Niño years) and years of “below-normal rains” (herein referred to as La Niña years) which are associated and modulated by El Niño southern oscillation. They also reveal that drought years tend to occur in succession and that the June winds tend to be suppressed or absent during El Niño years, but strongly associate with La Niña years. The study suggests that the frequency and therefore the ratio of La Niña years to El Niño years have been increasing. The study also suggests possibility of developing a decision support system for farmers in resource use and allocation based predicted time of occurrence of the June winds.

Analysis of mealybug incidence on the cotton crop using ADSS-OLAP (Online Analytical Processing) tool

Traditionally the agriculture expert's knowledge is descriptive and experimental, therefore, it is difficult to describe it mathematically and subsequently build agriculture Decision Support Systems (DSS). Furthermore, the corresponding data may be in such a raw form that it cannot be used in a DSS. The Agriculture Decision Support System (ADSS) is a 26-month project based on the Agro-met data from 2001 to 2006 of Punjab (the bread-basket of Pakistan), its ADSS-OLAP, i.e. Online Analytical Processing tool ( www.agroict-olap.org) allows for quick analysis of all possible interesting aggregates of the ADSS data by employing drag-drop and mouse-click and is used in this paper to identify the effective pesticide groups related to the mealybug incidence. Pakistan is the world's fifth-largest producer of cotton, but the emergence of the mealybug as a new cotton pest is likely to reduce the cotton yield by 1.3 million bales. The research work reported in this paper is based on the detailed pest-scouting data of 2300+ farmers of District Multan (cotton hub of Pakistan) for the years 2005 and 2006. This paper will also provide guidelines for the design and development of similar complex systems/tools and discusses the issues of agricultural data-quality management, particularly in the field of insect-pest management.

SUSTAINABLE AGRICULTURAL DEVELOPMENT: KNOWLEDGE‐BASED DECISION SUPPORT

The article introduces the knowledge‐based agricultural decision support system. The system includes database and knowledge base as well as modules used for formation of models, optimization, simulation, decision analysis and inference. The linear programming model contains several hundreds of variables and restrictions. The farm model, using entered data, is formed according to “if‐then” type rules that are stored in the knowledge base. Having solved the task of optimization, the particular values of variables indicate what kind of crops should be grown and in what area, as well as what animals and how many of them should be kept and what resources and how much of them have to be used for achieving the biggest benefit under the environmental and other conditions. The simulation was employed to test the sensitivity of the plan to weather and market variations. Having applied a set of production rules to the given facts and modelling results within the module of decision analysis and inference, conclusions and suggestions are made. Decision support system performs the analysis of production efficiency, resource reserves and shortage, and with the help of the Internet in real time provides a farmer with conclusions and suggestions necessary to increase the efficiency of production conforming to environmental constraints. The integration of optimization calculations and knowledge management into the agricultural decisions‐support system expands its possibilities and improves the quality of solutions. Santrauka Pristatoma žiniomis grįsta žemės ūkio sprendimų paramos sistema. Ją sudaro duomenų ir žinių bazės, modelių formavimo, optimizavimo, imitavimo, sprendimų analizės ir išvadų formavimo moduliai. Žemės ūkio įmonės modelis sudaromas pagal įvestus duomenis, remiantis žinių bazėje saugomomis „jeigu–taip“ tipo taisyklėmis. Išsprendus optimizavimo uždavinį gautos kintamųjų vertės rodo, kokie javai ir kokiame plote turi būti auginami, taip pat kokie gyvuliai ir kiek jų turi būti laikoma, kokie ištekliai ir kiek jų turi būti panaudota, norint pasiekti didžiausią naudą ūkyje nurodytomis aplinkosaugos ir kitomis sąlygomis. Imitavimo būdu patikrinamas gamybos plano jautrumas orų ir rinkos pokyčiams. Išvadų formulavimo modulyje, pritaikius duotiems faktams ir modeliavimo rezultatams produkcinių taisyklių rinkinį, gaunamos išvados bei pasiūlymai. Sprendimų paramos sistema atlieka gamybos efektyvumo, išteklių rezervų bei išteklių trūkumo analizę. Ūkininkas internetu gauna išvadas bei pasiūlymus, kaip didinti gamybos efektyvumą. Optimizavimo skaičiavimų ir žinių bazės integravimas į žemės ūkio sprendimų paramos sistemą išplečia jos galimybes ir pagerina sprendimų kokybę.

Development of a Management Tool to Indicate the Environmental Impact of Organic Viticulture

Organic viticulture is an important part of the European Union organic farming sector, and, according to the most recent surveys, 1.5% of European Union wine originates from organic farms, with an upward trend. This paper describes an environmental impact of an organic viticulture indicator (EIOVI) that can be reliably used in the management of organic vineyards. The EIOVI can be used as a decision support system for farmers and other property managers by evaluating the potential ecological impact of their choices, thus optimizing management options. The tool allows the simulation of vineyard management based on six agricultural and ecological modules. The EIOVI is a fuzzy expert system that calculates the relationship between the modules on the basis of a set of 64 decision rules. Initial testing (validation) has been performed using 20 simulations for six Swiss wine-growing estates. The results of these tests were promising; the EIOVI motivates managers to consider the wine-growing estate as a whole by subsummarizing all aspects of management. The visualization of results is very tangible and clearly shows that the use of this indicator could improve the management of the vineyard. With some improvements, the EIOVI will be a helpful assessment tool for vine growers, consultants, environmental agencies, and scientists.

A qualitative case study of the adoption and use of an agricultural decision support system in the Australian cotton industry: The socio-technical view

In response to the call for research that considers the human as well as the technical aspects of information systems implementation, the authors report on an interpretive case study which explores the adoption and use of an agricultural decision support system (DSS) CottonLOGIC in the Australian cotton industry. The study was informed through the innovation-decision model by Rogers and the technology-in-practice model by Orlikowski using a socio-technical approach. It was found that participants who achieved a high level of implementation success were reflexive and resourceful in adapting the technology to their changing needs, often in ways unanticipated by DSS builders.

Wither agricultural DSS?

Computer-based agricultural decision support systems (aDSS) may be argued to have passed sequentially through phases of unbelief, euphoria and disappointment, and to be currently passing into either a phase of maturity with realistic expectations of the technology, or to abandonment. This paper appraises, in the context of the DSS development literature, our past and current efforts in decision support using simulation-models and farm-scale case-studies. The paper first reviews some of the explanations for the lack of success for aDSS including the identification of suitable roles and how best the tools may be deployed. The paper then outlines the authors’ experiences during the euphoric period of aDSS development including the undertaking of market research on the nature of the aDSS desired and their potential for commercialisation. The positive outcome of the market research was that potential end-users recognised the range of functionality that an aDSS could offer. There was, however, significant scepticism on the balance of costs and benefits. The end-user preference for aDSS delivered as software products for use in-house, when combined with the limits on the price-per-unit that the market would bear, meant that there was little commercial potential. In the light of these findings the team re-evaluated the role and development strategy for their aDSS. The paper outlines this strategy in terms of both the technical developments of the aDSS and the approach to its use with stakeholders. The paper then discusses the legacy from the euphoric period highlighting a number of socio-political and institutional barriers to the use of aDSS which remain to be overcome. The paper concludes by arguing that there is a need to think beyond technocentric solutions to overcome the barriers to wider aDSS use and that there are a number of models of best-practice for aDSS development that can ensure their relevance.

Agriculture and forestry economy decision support system based on agent

In this paper, we focus on the common problems of current information analysis and support decision systems in agricultural and forestry economies, such as frequent manual interventions, lack of cooperation among sub‐systems, lack of support from distributed computing and group decision making. This research aims to resolve these problems by rebuilding the system with agent technology, and a prototype of the agricultural and forestry economy decision support system (AFEDSS) based on agent is designed and implemented. The AFEDSS is composed of interface agent, management agent, model agent, forecast agent, assistant decision agent, data management agent. The results show that the new system can simulate and deal with the complex processes of agricultural and forestry economies in reasonably short computational times and with less subjective uncertainty. This paper also discusses the decision processes and internal mechanisms in AFEDSS especially on cooperating with dynamic analysis, evaluation, forecast and optimisation.