In Silico Farming

A computational method that optimizes crop growth. It collects data from real crops in the field and creates a mathematical model to simulate how yields perform under any given circumstance. This solution helps crops grow more efficiently.
Technology Life Cycle

Technology Life Cycle


Initial phase where new technologies are conceptualized and developed. During this stage, technical viability is explored and initial prototypes may be created.

Technology Readiness Level (TRL)

Technology Readiness Level (TRL)

Field Validation

Validation is conducted in relevant environments, where simulations are carried out as close to realistic circumstances.

Technology Diffusion

Technology Diffusion


First to adopt new technologies. They are willing to take risks and are crucial to the initial testing and development of new applications.

In Silico Farming

In silico studies are computer simulations with 3D models reflecting the real world as closely as possible. Unlike digital twins, in silico designs can react to specific inputs and provide conclusions for further analysis. In silico farming is a farming ecosystem transformed into code, where planting patterns, tillage systems, sunlight and shading, water availability, microbial interactions, and many other variables are digitally tested. By modeling the coupled plant-soil atmosphere management ecosystem, the simulated spatial resolution and precision output could potentially be comparable to having a large number of physical sensors distributed in the field.

Recently, in silico trials are being applied in crop science to monitor highly accurate digital plants to help speed up selective breeding. Accordingly, researchers can build statistical models that identify mathematical relationships using agricultural data and then create simulations based on those equations, allowing the measured traits to play out on the screen. Once they visualize the crops, scientists can manipulate the data to see which factors result in the fastest-growing, most drought-resistant, or least pest-susceptible plants possible.

Currently, this method cannot help individual farmers to manage their operations. It is mainly used by international organizations, national governments, and multinational corporations that run what-if scenarios about climate change and agriculture policy.

Future Perspectives

In silico farming is a bottom-up approach, meaning the process begins by simulating the properties of individual plants and then extrapolating the data and behavior to determine the yield for whole crops. Machine learning methods, on the other hand, offer a top-down approach to crop prediction. It processes data captured by drones and satellites with publicly available remote sensing data, subsequently tracking and predicting the impact of environmental factors on crops, including weather changes, soil parameters, and possible plant diseases.

The integration of top-down predictive models with bottom-up simulations at the individual plant level would make it possible to reap the best of both worlds: high spatial resolution and sound predictive forecasts for entire crops. In the future, instead of merely responding to food shortages, it could be possible to preemptively set appropriate food reserve levels, identify low-yield regions, and predict where to send food aid. If computer simulations scale up, they could boost the democratization of precision, taking mono, polyculture, and agroforestry farming to new levels.

Image generated by Envisioning using Midjourney

Scientific American is the essential guide to the most awe-inspiring advances in science and technology, explaining how they change our understanding of the world and shape our lives.
This book explores the role of in silico deployment in connection with modulation techniques for improving sustainability and competitiveness in the agri-food sector; pharmacokinetics and molecular docking studies of plant-derived natural compounds; and their potential anti-neurodegenerative activity. It also investigates biochemical pathways for bacterial metabolite synthesis, fungal diversity and plant-fungi interaction in plant diseases, methods for predicting disease-resistant candidate genes in plants, and genes-to-metabolites and metabolites-to-genes approaches for predicting biosynthetic pathways in microbes for natural product discovery. The respective chapters elaborate on the use of in situ methods to study biochemical pathways for bacterial metabolite synthesis; tools for plant metabolites in defence; plant secondary metabolites in defence; plant growth metabolites; characterisation of plant metabolites; and identification of plant derived metabolites in the context of plant defence. The book offers an unprecedented resource, highlighting state-of-the-art research work that will greatly benefit researchers and students alike, not only in the field of agriculture but also in many disciplines in the life sciences and plant sciences.
In silico modelling, in which computer models are developed to model a pharmacologic or physiologic process, is a logical extension of controlled in vitro experimentation. It is the natural result of the explosive increase in computing power available to the research scientist at continually decreasing cost. In silico modelling combines the advantages of both in vivo and in vitro experimentation, without subjecting itself to the ethical considerations and lack of control associated with in vivo experiments. Unlike in vitro experiments, which exist in isolation, in silico models allow the researcher to include a virtually unlimited array of parameters, which render the results more applicable to the organism as a whole. In silico modelling is best known for its extensive use in pharmacokinetic experimentation, the best-known example of which is the development of the three-compartment model. In addition, complex in silico models have been applied to pathophysiological problems to provide information which cannot be obtained practically or ethically by traditional clinical research methods. These experiments have led to the development of significant insights in subject matters ranging from pure physiology to congenital heart surgery, obstetric anaesthesia airway management, mechanical ventilation and cardiopulmonary bypass/ventricular support devices. The utility of these models is based on both the validity of the model framework as well as the corresponding assumptions. In vivo experimentation has validated some, but not all of the in silico strategies employed. We present a review illustrating by example how in silico modelling has been applied to a number of cardio-respiratory problems in states of health and disease, the purpose of which is to give the reader a sense of the complexity and assumptions which underlie this diverse and underappreciated research strategy, as well as an introduction to a research strategy that will likely continue to grow in importance.
This paper presents an artificial neural network model for crop yield responding to soil parameters. The experimental data had been obtained via a precision agriculture experiment, which is carried...
Sugarcane has emerged as the second largest source of biofuel, primarily as ethanol produced in Brazil. Dual row planting using asymmetric spacing of rows can decrease damage to plants and soil...
Agroforestry has large potential for carbon (C) sequestration while providing many economical, social, and ecological benefits via its diversified products. Airborne lidar is considered as the most accurate technology for mapping aboveground biomass (AGB) over landscape levels. However, little research in the past has been done to study AGB of agroforestry systems using airborne lidar data. Focusing on an agroforestry system in the Brazilian Amazon, this study first predicted plot-level AGB using fixed-effects regression models that assumed the regression coefficients to be constants. The model prediction errors were then analyzed from the perspectives of tree DBH (diameter at breast height)—height relationships and plot-level wood density, which suggested the need for stratifying agroforestry fields to improve plot-level AGB modeling. We separated teak plantations from other agroforestry types and predicted AGB using mixed-effects models that can incorporate the variation of AGB-height relationship across agroforestry types. We found that, at the plot scale, mixed-effects models led to better model prediction performance (based on leave-one-out cross-validation) than the fixed-effects models, with the coefficient of determination (R2) increasing from 0.38 to 0.64. At the landscape level, the difference between AGB densities from the two types of models was ~10% on average and up to ~30% at the pixel level. This study suggested the importance of stratification based on tree AGB allometry and the utility of mixed-effects models in modeling and mapping AGB of agroforestry systems.
There are many different types of potential applications of AI in agriculture -- ranging from machine control, to image analysis, to improving our understanding of where, when, and how a crop might respond toparticular environmental conditions.
Precision forestry could improve forest management significantly. What areas are most promising, and how can forestry companies start their digital transformation?
•Data limitations exist for all components of agricultural systems.•Model limitations also exist, more severely in constrained, complex systems.•Knowledge products for informing decisions and policy remain very limited.•Use cases provide an important context for model evaluation and improvement.•More emphasis is needed on models, systems analyses of agricultural systems.
Big data is revolutionizing agricultural innovation – but not just through precision agriculture. For the last few years, we’ve heard about the role big data analytics can play to advance agriculture through precision agriculture and farmer practices. But there are other applications of big data that can have a profound impact on crop performance.

Interested in our research?

Read about our services for help with your foresight needs.