Periodic Reporting for period 2 - Trapview (Trapview - Automated pest-monitoring system for sustainable growing with optimal insecticide use)
Berichtszeitraum: 2017-09-01 bis 2018-08-31
The Food and Agriculture Organization of the UN (FAO) is expecting that the world population will grow to 9 billion by 2050. This 25 percent population growth will require a similar growth of food production, mostly through increasing the size of arable land and productivity (crop yields). Pest insects are one of the major obstacles in increasing food production. They destroy approximately 14 percent of all annual crop production. Each year, almost 5 million tons of more than 600 different pesticide types are applied but only 1 percent is effective. This means that 99 percent of sprayed pesticides are released to non-target soils, water bodies and atmosphere, and absorbed by practically every living organism. In addition to health and environment risks, there is also the risk that pests become resistant to pesticides because many growers are spraying too much or spraying at the wrong time. As a consequence, target pests become resistant to a particular chemical substance, rendering it ineffective for future use.
Assessment of the exact time for spraying is usually made based on information gathered from pheromone traps for monitoring insect population. This is very labor intensive and time consuming. The time needed to reach a proper crop protection decision often surpasses the time window for optimal crop protection application. If growers were alerted in real-time when the number of pests reached the economic threshold levels, insecticide efficiency would increase by more than 30 percent. Growers, especially those with more than 100 hectares of crop land, are interested in solutions for daily pest monitoring that would help them decrease pest control expenses and use less pesticide.
Therefore, overall objectives for the Trapview project are to:
• Reduce the expense of growing healthy food (decrease cost of manual field inspections and insecticide use).
• Reduce the amount of insecticide residues in food due to more optimal spraying times.
• Decrease the probability of pest insects becoming resistant to insecticides.
• Enable real-time alerts about insect pest situation in the fields for determining exact time to spray to achieve optimal pesticide efficiency.
In order to achieve these, the following project goals were set for the project:
• Develop reliable, robust and completely self-sustainable low-maintenance automated pest monitoring traps with functional mechanism for changing sticky plates.
• Improve accuracy of the state-of-the-art computer vision system that automatically identifies the pest insects in the images taken by automated traps.
• Further develop web and mobile applications that would serve the pest related information to Trapview users in real-time.
• Predict insect occurrences on a broader geographical scale (where pest insects occur and how they move across regions) and commercialize the pest information.
Assessment of the exact time for spraying is usually made based on information gathered from pheromone traps for monitoring insect population. This is very labor intensive and time consuming. The time needed to reach a proper crop protection decision often surpasses the time window for optimal crop protection application. If growers were alerted in real-time when the number of pests reached the economic threshold levels, insecticide efficiency would increase by more than 30 percent. Growers, especially those with more than 100 hectares of crop land, are interested in solutions for daily pest monitoring that would help them decrease pest control expenses and use less pesticide.
Therefore, overall objectives for the Trapview project are to:
• Reduce the expense of growing healthy food (decrease cost of manual field inspections and insecticide use).
• Reduce the amount of insecticide residues in food due to more optimal spraying times.
• Decrease the probability of pest insects becoming resistant to insecticides.
• Enable real-time alerts about insect pest situation in the fields for determining exact time to spray to achieve optimal pesticide efficiency.
In order to achieve these, the following project goals were set for the project:
• Develop reliable, robust and completely self-sustainable low-maintenance automated pest monitoring traps with functional mechanism for changing sticky plates.
• Improve accuracy of the state-of-the-art computer vision system that automatically identifies the pest insects in the images taken by automated traps.
• Further develop web and mobile applications that would serve the pest related information to Trapview users in real-time.
• Predict insect occurrences on a broader geographical scale (where pest insects occur and how they move across regions) and commercialize the pest information.
The report covers a period from 1st September 2016 to 31st August 2017. During the reporting period work was commenced in all areas of work: Hardware and Software development, Development of Image recognition and Machine Learning algorithms, Trap network building, Sales, Communication and Dissemination, etc.
The most notable results have been achieved in the area of HW development and Image Recognition. We have successfully launched trap self-cleaning mechanism, which reduces the need for manual changing of the sticky plates and thus reducing growers’ travel expenses. The innovation used in the network of already saved thousands of kilometers and hours of manual labor, proved to be reliable and is fully capable of reaching the objective set out in the project charter. As experienced in one of the cases, one self-cleaning mechanism saved the grower 17(!) travels to the trap in only one month.
One of the main goals of the project is to develop and improve accuracy of the state-of-the-art computer vision system. Initial results of testing of newly developed Deep Learning Neural Networks algorithm have significantly surpassed our expectations as the new algorithm is achieving more than 90% of accuracy. It is necessary to point out that such accuracy is far better than human and anything else that is currently available in the market. Nevertheless, there is plenty of work to be done especially in the area of continuous learning process of neural networks and increasing robustness of the algorithms when it comes to mixed pest population on the same sticky plates (avoiding false positives).
By the date of this report there were eleven trap clusters in operation consisting of several hundred traps in 11 South European countries. The network is made of the same type of traps, attracting insects with the same pheromone lure and thus enabling statistical consistency of the data collected. Unification of the traps and the number of traps in the network itself provide consistent quality data, which is also statistically representative. This is vital for building statistical models and data analysis in order to deliver pest forecast.
The project also allowed us to reach out to much larger audience by attending large number of different events (pitching, investors’, etc.), tradeshows, fairs, specialized events for growers and be present in the general public media (national television and newspapers). All the activities in the communication and dissemination area reflected also in the sales results as we have been able to successfully follow the company growth plans outlined in the project charter.
The most notable results have been achieved in the area of HW development and Image Recognition. We have successfully launched trap self-cleaning mechanism, which reduces the need for manual changing of the sticky plates and thus reducing growers’ travel expenses. The innovation used in the network of already saved thousands of kilometers and hours of manual labor, proved to be reliable and is fully capable of reaching the objective set out in the project charter. As experienced in one of the cases, one self-cleaning mechanism saved the grower 17(!) travels to the trap in only one month.
One of the main goals of the project is to develop and improve accuracy of the state-of-the-art computer vision system. Initial results of testing of newly developed Deep Learning Neural Networks algorithm have significantly surpassed our expectations as the new algorithm is achieving more than 90% of accuracy. It is necessary to point out that such accuracy is far better than human and anything else that is currently available in the market. Nevertheless, there is plenty of work to be done especially in the area of continuous learning process of neural networks and increasing robustness of the algorithms when it comes to mixed pest population on the same sticky plates (avoiding false positives).
By the date of this report there were eleven trap clusters in operation consisting of several hundred traps in 11 South European countries. The network is made of the same type of traps, attracting insects with the same pheromone lure and thus enabling statistical consistency of the data collected. Unification of the traps and the number of traps in the network itself provide consistent quality data, which is also statistically representative. This is vital for building statistical models and data analysis in order to deliver pest forecast.
The project also allowed us to reach out to much larger audience by attending large number of different events (pitching, investors’, etc.), tradeshows, fairs, specialized events for growers and be present in the general public media (national television and newspapers). All the activities in the communication and dissemination area reflected also in the sales results as we have been able to successfully follow the company growth plans outlined in the project charter.
The implementation of the technical innovations described above already produced considerable results. The impact that we were able to measure directly during the first period of the Trapview project was the effect of self-cleaning mechanism on overall sustainability of the farm operations. The farmers’ field work analysis shows significant decrease of travels needed to maintain the pest monitoring traps, which directly means reduction of fuel consumption, CO2 emissions, manual work labor, etc. In average our traps have already saved more than 36.000 km of travels and 1.170 hours of manual work that can be now spent on other even more meaningful tasks.
As result of market analysis of one of the key customer segments, an estimation of the savings if the insecticides are used at optimal time, was calculated. Insect related damage accounts for approximately 10% of total production value of the analysed crop. If growers are able to minimize the damage caused by insects (save 10%) by using Trapview that would mean savings of several hundred EUR per hectare, which is almost five times more than what we have estimated initially and is far more than the required investment.
In addition of what we have already described above, the results clearly show direct improvements of major sustainability key performance indicators, which in addition to be more sustainable enable the growers using Trapview as a measurement and proofing tool to build a better public and market brand recognition. This results in obtaining higher prices of produce towards the tomato processing companies, who are willing to pay premium purchase prices for the high quality produce.
All results described above are meeting or surpassing our expectations. Trapview project is allowing us to introduce innovations that enable food growers and our company to be more competitive than ever and impact society and the way how food is grown on a global scale.
As result of market analysis of one of the key customer segments, an estimation of the savings if the insecticides are used at optimal time, was calculated. Insect related damage accounts for approximately 10% of total production value of the analysed crop. If growers are able to minimize the damage caused by insects (save 10%) by using Trapview that would mean savings of several hundred EUR per hectare, which is almost five times more than what we have estimated initially and is far more than the required investment.
In addition of what we have already described above, the results clearly show direct improvements of major sustainability key performance indicators, which in addition to be more sustainable enable the growers using Trapview as a measurement and proofing tool to build a better public and market brand recognition. This results in obtaining higher prices of produce towards the tomato processing companies, who are willing to pay premium purchase prices for the high quality produce.
All results described above are meeting or surpassing our expectations. Trapview project is allowing us to introduce innovations that enable food growers and our company to be more competitive than ever and impact society and the way how food is grown on a global scale.