Technologies > Open Big Data Platform For Farming

Open Big Data Platform For Farming
Innovation in agro-technology will propel a sustainable and intensive crop production and for driving innovation for the Danish agricultural business sector. One of the most important challenges for farming is to increase plant production per hectare, while at the same time reducing the impact on the environment. The solution is to create decision support systems to make production more intelligent, sustainable and efficient throughout the entire value chain from technology provider to farm production.  Decision support systems (DSS) aided by machine learning algorithms is the new expertise at Absolutum soleil. This project aims for creation of an open data platform for Big Data analytics and Information management for decision support in precision farming of the future.

Technical equipment such as drones, sensors, cameras and computational solutions to handle and interpret production related data will give Danish farmers a potential to expand production in farms. The project concerns the research and development of a robust, scalable, and secure data platform for providing decision support in future farm production. The data platform integrate data from distributed information sources to provide new technologies, solutions and decision support techniques for modern high yielding and low emission precision farming. It will be open to third party such as consultants and software developers that may desire to contribute and offer a direct and documented value-add for farmers and suppliers. The research and development bases on the state of the art in cloud computing, distributed middleware, cyber security, and privacy enforcement technologies among others.

Opendata for the different farm management information systems (FMISs) must be designed to accommodate the aforesaid differences among the European regions. Current farm management information systems do not interoperate well due to proprietary formats and the lack of agreed standards; and most commercial solutions are limited by a vertical integration. To circumvent this, the new platform will provide data for optimization at farm level and beyond based on distributed heterogeneous data sources, while providing proper quality, security, and privacy guarantees. The data platform will integrate heterogeneous data, validate and analyze it, to allow cost-effective monitoring, quality assurance, and performance analysis. Accessibility of data is the key challenge for Big Data to bring data together, run the proper analytics and make use of massively parallel and super-computing technologies.

This project has the following stages
Stage-I : Big Data Architecture design with focus towards Open data platform
Stage-II : Collection,  Processing, Providing and Using Data for farmers through Cloud services.
Stage-III: Predictive analytics from Open Data

Expected results : 
I. A computer model to integrate the various data into a simulation of the growing conditions in the field.  Software-only analytics that take sensor data from the farm, combine it with outside data like weather data and aerial imaging, to give farmers information on what’s going on in their fields. 
II. Open data platform delivered via cloud services, running on Amazon EC2 with an additional cloud storage provider  typically offering software platforms/API that provide digital imagery along with crop analysis  and field scripts.
III. Advanced data analytics package to figure out the optimization of crop yields based on combined data sets from weather patterns and soil data with help of weather data analytics firm and a soil testing labs. A software solution that enables farmers to design the optimal planting environments for their crops on new farms or to select crops with yields optimized to the planting environment on existing farms.

Farming has always been as much art as science: knowing what to plant and when is often intuitive for many farmers. However the vagaries of shifting weather patterns and climate change make this much more difficult and a crop destroyed by inclement weather or drought may cost small hold farmers and their families their livelihood. There are predictions of massive crop yield fall offs in the coming decades thanks to climate change, such predictive computer modelling is going to become increasingly necessary to test a new setup that combines a network of field sensors and atmospheric observations with a supercomputer to create hyperlocal forecasts at super fine resolutions. The adoption rates for the system could be considerably lower than expected and the increased availability of computers on farms did not automatically result in the use of the computer for farm management. The project can observe the importance of involving the end-users in the development of the system and – as with any information system for agriculture- localisation and usability are critical issues for the overall success of the system

List of references :
Anon.,2002.Field Operations Data Model—General Overview. Overview.pdf 
Anon., 2008. PostGIS. 
Moran, M.S., 2000: "Technology and techniques for remote sensing in agriculture," Assoc. Appl. Biol. and Rem. Sens. Soc. Conf. on Remote Sensing in Agriculture; June 26-28, Cirencester, England; p. 1-10.
Chaudhary, S., Sorathia, V., Laliwala, Z., 2004. Architecture of sensor based agricultural information system for effective planning of farm activities. In: Proceedings of the 2004 IEEE International Conference on Services Computing, SCC 2004, pp.93–100.
Danish Agriculture, 2007. Danish Agriculture in Numbers. Land Economic Outlook 2007
Fountas, S., Ess, D., Sørensen, C.G., Hawkins, S., Blumhoff, G., Blackmore, S.,Lowenberg-DeBoer, J., 2005. Farmer experience with precision agriculture in Denmark and the US eastern corn belt. Precision Agriculture 6, 121–141
Gasser, U., Palfrey, J., 2007. Breaking Down Digital Barriers: When and How ICT Interoperability Drives Innovation. Berkman Publication Series, November 2007
Linseisen, H., Spangler, A., Hank, K. (2000): Daten, Datenströme und Software in einem Informationssystem zur teilflächenspezifischen Pflanzenproduktion, Zeitschrift für Agrarinformatik, Vol. 2, pp. 36–42
Linseisen, H., 2001. Development of a precision farming information system. In:Proceedings of the Third European Conference on Precision Agriculture, Montpellier, pp. 689–694.
Rains, G.C., Thomas, D.L., 2000. Precision Farming–An Introduction. Georgia Extension Bulletin, US.
Mo, X., Liu, S., Lin, Z., Xu, Y., Xiang, Y., McVicar, T.R., 2004. Prediction of crop yield, water consumption and water use efficiency with a SVAT-crop growth model using remotely sensed data on the North China Plain. Ecol. Model. 183, 301–322.
Oksanen, T., Suomi, P., Visala, A., Haapala, H., 2005. ISOBUS compatible implements in the project AGRIX. In: Stafford, J.V. (Ed.), Precision Agriculture’05. CSIRO Publishing, pp. 565–572.
Ohlmer, B., Olson, K., Brehmer, B., 1998. Understanding farmers’ decision making processes and improving managerial assistance. Agricultural Economics 18, 273–290
Santana, F.S., Murakami, E., Saraiva, A.M., Correa, P.L.P., 2007. A Comparative Study between Precision Agriculture and Biodiversity Modelling Information Systems. In: EFITA / WCCA 2007–6th Biannual Conference of the European Federation of IT in Agriculture, pp. 1–6.
Schmitz, M., Martini, Kunisch, M., MÃsinger, H-J., 2008. agroXML enabling standardized, platform-independent internet data exchange in farm management information systems. In: Metadata and Semantics, Springer, US, pp. 463– 468
Sørensen, C.G. and Bochtis, D.D. (2010): Conceptual model of fleet management in agriculture, Biosystems Engineering, Vol. 105, no. 1, pp. 41–50.
Sørensen, C., Bildsøe, P., Fountas, S., Pesonen, L., Pedersen, S., Basso, B., Nash, E., 2009. Stafford, J.V., 2000. Implementing Precision Agriculture in the 21st Century. J. Agric. Eng. Res. 76, 267–275.System Analysis and Definition of System Boundaries. FutureFarm, Report No. 3.1,
Suomi, P., Visala, A., Haapala, H., 2005. ISOBUS compatible implements in the project AGRIX. In: Stafford, J.V. (Ed.), Precision Agriculture’05. CSIRO Publishing, pp. 565–572