Our Technologies

ListenField specializes in the gathering, processing and analyzing of multilayer data to provide insightful information to agro professionals.

Aggregation of Agro-Environmental Data


Agro-environmental data provide relevant and accurate information to improve agricultural practices and outcomes. However, data is difficult to obtain because it is usually scattered and highly complex. ListenField provides various APIs that efficiently bring these data together and perform systematic analyses of these data, allowing our customers to seamlessly and precisely monitor the condition of their fields.


This includes for example a “soil fusion” model that assesses the soil profile deeper down to 60 centimeters anywhere. This information is available for anyone using the API. We are also utilizing up to 30 years of historical weather data and onsite sensors to accurately predict seasonal weather conditions at precise locations. Combining real-time sensor readings, with historical weather data is more effective in anticipating short-term weather trends. Lastly, the “cultivar file” that ListenField has put together can help you by telling how your plants are growing under prevailing conditions, or how your crops will turn out if they are fed differently or if climate and soil conditions change.

Crop Health Monitoring


ListenField is developing machine vision models that empower satellite imagery analysis to help you determine the health of your crop regarding to their phenology stage. ListenField crop heath can help determine whether crops have enough fertilizers at a particular location in a plot of land, to let you add or reduce the amount of fertilizers accordingly. The technology can also tell us about “water stress”, in certain crops like orange trees.


ListenField has been developing a machine vision model that empowers satellite imagery analysis to help you determine the health of your crop depending on their phenology stage. It can help determine whether crops have enough fertilizers at a particular location in a plot of land. Fertilizers can then be added or reduced to ensure optimal “nitrogen stress” translating into more output, more stable output, and better output quality. It can also reduce the risk of “lodging” for crops such as rice and wheat -- where the stem of the plant bends over, making it very difficult to harvest the grain and greatly reducing yield.


The technology can also tell us about “water stress”, for example, in orange trees where not enough water would obviously endanger the survival of the orange tree, but just enough “water stress” will increase the sweetness of the fruit.

Growth and Quality Prediction


ListenField provides yield and growth prediction by considering the 3 important factors

The first is soil. We built what we called a “soil fusion” model that assessed the soil profile. This information is available for anyone using APIs.

The second is climate and weather conditions. For this, we used 30 years of climatological data as the benchmark. This weather pattern data is used to more accurately predict seasonal weather conditions at precise locations with the help of onsite sensors. These sensors monitor rainfall and combined with past data and can be used to anticipate short-term trends.  They also monitor moisture and other factors that are important for plant growth. Our models will provide detailed and timely data on climate conditions as well as their outlook at precise locations anywhere.


The third is the cultivar coefficient. It means that plants, each with their unique genotypes, will grow and reproduce differently in response to changing environmental conditions. The “cultivar file” that ListenField has put together can help tell you how your plants are growing under prevailing conditions. Even better, it can also tell you how your crops will turn out if they are fed differently or if climate and soil conditions change.

Phenotype and Genotype Analysis


ListenField is currently developing two predictive models for a web application. One is a model for genomic selection (GS) and another one is for genome-wide association studies (GWAS).


The models help to shorten the breeding time and thus fulfill several key goals related to the use of genetic resources and in the end the sustainability of agricultural production.


The GS model can predict the likelihood for phenotypic outcomes for specific traits (e.g. sugar content) based on (marker-based) genomic selection. It presents the data in an easy-to-understand way for user judgement.


The GWAS model assesses which gene-markers are associated with a certain variation in the phenotype (which gene-sequence is highly correlated to a phenotypic trait).

See what ListenField can do to improve your operations and profitability

Contact Us