Periodic Reporting for period 1 - SIAM (Source Integration for Agriculture Management)
Reporting period: 2016-05-01 to 2016-10-31
Two themes help to provide context for the SIAM project so far: agricultural innovation and macro-environmental challenges. Innovations in the agricultural sector have always been the driving force behind increases in productivity. The innovations of the green revolution have led to large increases through better plant varieties, pesticides, fertiliser and irrigation. Without these innovations global markets would not be able to feed the current population of over seven billion people. Equally the agricultural sector is in a different place compared to the second half of the 20th century. Climate change, shrinking land and water resources, land degradation and pollution impose massive challenges on food security. Improvements in agricultural practice are essential to meeting these challenges and that is where SIAM’s technological offering comes in.
SIAM stands for Source Integration for Agricultural Monitoring and is an unrivalled data processing structure that applies advanced data analytics to deliver detailed, high quality, and physically quantified data on crop and water conditions (CWC) at field level. In doing so SIAM brings new revolutionary features in data-fusion being the integration of 1) optical satellite data, 2) radar satellite data, 3) UAV/Drone data, and 4) ground based measurements. Sources 2, 3 and 4 are not hampered by clouds, increasing the applicability of SIAM data in cloud prone regions.
The overall objective of SIAM is to redefine data quality standards to support agricultural productivity improvements, respond to the opportunities in the precision farming market at present and deliver high quality CWC data at affordable prices. The potential that has been identified in Europe’s smart farming sector make it the primary target for SIAM technology. Furthermore eLEAF will bring to market a new sort of CWC data that meets the standard required for additional innovation in smart farming techniques. It will enable information driven innovation, supporting highly needed productivity increases and improvements in resource use efficiency. This will enhance the resilience of Europe’s agricultural sector with regard to climate change and improve its competitiveness on the global market.
SIAM stands for Source Integration for Agricultural Monitoring and is an unrivalled data processing structure that applies advanced data analytics to deliver detailed, high quality, and physically quantified data on crop and water conditions (CWC) at field level. In doing so SIAM brings new revolutionary features in data-fusion being the integration of 1) optical satellite data, 2) radar satellite data, 3) UAV/Drone data, and 4) ground based measurements. Sources 2, 3 and 4 are not hampered by clouds, increasing the applicability of SIAM data in cloud prone regions.
The overall objective of SIAM is to redefine data quality standards to support agricultural productivity improvements, respond to the opportunities in the precision farming market at present and deliver high quality CWC data at affordable prices. The potential that has been identified in Europe’s smart farming sector make it the primary target for SIAM technology. Furthermore eLEAF will bring to market a new sort of CWC data that meets the standard required for additional innovation in smart farming techniques. It will enable information driven innovation, supporting highly needed productivity increases and improvements in resource use efficiency. This will enhance the resilience of Europe’s agricultural sector with regard to climate change and improve its competitiveness on the global market.
As per the SME Instrument requirement for this period, work performed fell into one of three categories: technical, commercial and financial viability studies. An overview of the results from the technical viability studies includes a) the successful testing of SIAM data processing infrastructure using optical imagery from multiple satellites b) initial tests pertaining to UAV/drone data integration yielding a technically feasible conclusion with further testing ongoing c) the unequivocal technical feasibility of point source data to both improve and calibrate SIAM data analytics d) radar testing that concluded data from this source would be complementary and not applicable for full source integration. Continuous data validations in running projects confirm the accuracy of eLEAF’s proprietary algorithms.
Commercial viability studies included an exhaustive exploration of the potential of SIAM in light of current market conditions and industry trends. For example a) competitor analysis and market landscaping were conducted to ensure SIAM could be better understood in its commercial setting. This was conducted alongside b) sales channels and VAP assessments and c) a SWOT analysis. A further b) user needs verification testing was undertaken so that product/service delivery had been addressed and considered relative to SIAM competition and market expectation.
Financial viability testing during the period similarly included a) eLEAF profit and loss projections 2015-23 b) risk assessment and planning c) a marketing strategy outline and c) business model canvas. Both commercial and financial studies that were undertaken output positive results in relation to the SIAM programme.
Commercial viability studies included an exhaustive exploration of the potential of SIAM in light of current market conditions and industry trends. For example a) competitor analysis and market landscaping were conducted to ensure SIAM could be better understood in its commercial setting. This was conducted alongside b) sales channels and VAP assessments and c) a SWOT analysis. A further b) user needs verification testing was undertaken so that product/service delivery had been addressed and considered relative to SIAM competition and market expectation.
Financial viability testing during the period similarly included a) eLEAF profit and loss projections 2015-23 b) risk assessment and planning c) a marketing strategy outline and c) business model canvas. Both commercial and financial studies that were undertaken output positive results in relation to the SIAM programme.
SIAM progresses beyond the state of the art by providing smart farming with accurate quantified data based on proprietary algorithms operating in near real-time. Furthermore it harnesses an innovative data fusion protocol to aggregate multiple data sources. This new method of sourcing and analysing data would on its own be a progression beyond the state of the art in terms of improving the accuracy of remotely sensed data for crop monitoring purposes. Further to this, the SIAM programme addresses the scope of sensing technology on the market and seeks to fully explore and benefit from the synergies of data fusion. This involves understanding which elements of multiple source integration can benefit the crop monitoring process and in what capacity. Furthermore SIAM tackles the issue of insufficient satellite revisiting times by applying the best-data-available principle to its data processing infrastructure. This increases the flexibility of image analysis reducing the problem of cloud cover significantly by having a much higher change of capturing cloud free image of the set areas of interest. SIAM will be developed to serve as the backbone of eLEAF’s data processing infrastructure which will run continuously and as such should be seen as a strategic investment.
SIAM technology will have significant socio-economic impact. First, because using SIAM data higher yields can be obtained while using less water (more crop per drop). Second, the use of environmentally unfriendly inputs such as pesticides and fertilizer can be reduced. Third, SIAM data will allow the early scouting of food production variations across large areas, which is valuable for early mitigation of food security threats.
SIAM technology will have significant socio-economic impact. First, because using SIAM data higher yields can be obtained while using less water (more crop per drop). Second, the use of environmentally unfriendly inputs such as pesticides and fertilizer can be reduced. Third, SIAM data will allow the early scouting of food production variations across large areas, which is valuable for early mitigation of food security threats.