A Case Study of Environmental Benefits of Sensor-Based Nitrogen Application in Corn

Digital Transformation in Smart Farm and Forest Operations Needs Human-Centered AI: Challenges and Future Directions

The main impetus for the global efforts toward the current digital transformation in almost all areas of our daily lives is due to the great successes of artificial intelligence (AI), and in particular, the workhorse of AI, statistical machine learning (ML). The intelligent analysis, modeling, and management of agricultural and forest ecosystems, and of the use and protection of soils, already play important roles in securing our planet for future generations and will become irreplaceable in the future. Technical solutions must encompass the entire agricultural and forestry value chain. The process of digital transformation is supported by cyber-physical systems enabled by advances in ML, the availability of big data and increasing computing power. For certain tasks, algorithms today achieve performances that exceed human levels. The challenge is to use multimodal information fusion, i.e., to integrate data from different sources (sensor data, images, *omics), and explain to an expert why a certain result was achieved. However, ML models often react to even small changes, and disturbances can have dramatic effects on their results. Therefore, the use of AI in areas that matter to human life (agriculture, forestry, climate, health, etc.) has led to an increased need for trustworthy AI with two main components: explainability and robustness. One step toward making AI more robust is to leverage expert knowledge. For example, a farmer/forester in the loop can often bring in experience and conceptual understanding to the AI pipeline—no AI can do this. Consequently, human-centered AI (HCAI) is a combination of “artificial intelligence” and “natural intelligence” to empower, amplify, and augment human performance, rather than replace people. To achieve practical success of HCAI in agriculture and forestry, this article identifies three important frontier research areas: (1) intelligent information fusion; (2) robotics and embodied intelligence; and (3) augmentation, explanation, and verification for trusted decision support. This goal will also require an agile, human-centered design approach for three generations (G). G1: Enabling easily realizable applications through immediate deployment of existing technology. G2: Medium-term modification of existing technology. G3: Advanced adaptation and evolution beyond state-of-the-art.

Economic evaluation of variable rate nitrogen management of canola for zones based on historical yield maps and soil test recommendations

Canola (Brassica napus L.) is a highly valuable crop for Canada's economy, making the efficient management of canola a priority. A field-scale study was conducted at ten sites between 2014 and 2016 to evaluate the viability of site specific nitrogen (N) management zones (MZ) based on analysis of historical yield maps and soil test recommendations to improve canola productivity and profitability in western Canada. Treatments included factorial combinations of three canola yield zones (low, average, high) by four N rates, replicated four times at each site. The canola yield function had a quadratic form in each field but the effects of MZ varied between fields with positive effects in only a few fields. When ten site-years data were combined, MZ had positive effects on canola performance. On average, MZ of N fertilizer over ten fields generated between $28 to $65 ha^-1 more net revenue (NR) relative to average yield management. Site-years, which reflect farm management and other farm characteristics had significant effects on yield and NR ranging from - $91 to $352 ha^-1 compared to a baseline. Nitrogen application under MZs was only reduced by 8% compared to uniform rates. The potential for MZ does exist; however, its effectiveness is highly variable.

A scoping review of the digital agricultural revolution and ecosystem services: implications for Canadian policy and research agendas

The application of technologies such as artificial intelligence, robotics, blockchain, cellular agriculture, and big data analytics to food systems has been described as a digital agricultural revolution with the potential to increase food security and reduce agriculture’s environmental footprint. Yet, the scientific evidence informing how these technologies may impact or enhance ecosystem services has not been comprehensively reviewed. In this scoping review, we examine how digital agricultural technologies may enhance agriculture’s support of ecosystem services. Keyword searches in academic databases resulted in 2337 records, of which 74 records met review criteria and were coded. We identify three clusters of digital agricultural technologies including those that make farm management more precise, increase connectivity, and create novel foods. We then examine modelling and empirical evidence gaps in research linking these technologies to ecosystem services. Finally, we overview barriers to implementing digital agricultural technologies for better ecosystem services management in the Canadian context including economic and political systems; lack of policies on data management, governance, and cybersecurity; and limited training and human resources that prevents producers from fully utilizing these technologies.

A Sustainability Assessment of the Greenseeker N Management Tool: A Lysimetric Experiment on Barley

A preliminary study was conducted to analyze the sustainability of barley production through: (i) investigating sensor-based nitrogen (N) application on barley performance, compared with conventional N management (CT); (ii) assessing the potential of the Normalized Difference Vegetation Index (NDVI) at different growth stages for within-season predictions of crop parameters; and (iii) evaluating sensor-based fertilization benefits in the form of greenhouse gasses mitigation. Barley was grown under CT, sensor-based management (RF) and with no N fertilization (Control). NDVI measurements and RF fertilization were performed using a GreenSeeker™ 505 hand-held optical sensor. Gas emissions were measured using a static chamber method with a portable gas analyzer. Results showed that barley yield was not statistically different under RF and CF, while they both differed significantly from Control. Highly significant positive correlations were observed between NDVI and production parameters at harvesting from the middle of stem elongation to the medium milk stage across treatments. Our findings suggest that RF is able to decrease CO2 emission in comparison with CF. The relationship between N fertilization and CH4 emission showed high variability. These preliminary results provide an indication of the benefits achieved using a simple proximal sensing methodology to support N fertilization.

Life Cycle Assessment of Variable Rate Fertilizer Application in a Pear Orchard

Precision Agriculture (PA) is a crop site-specific management system that aims for sustainability, adopting agricultural practices more friendly to the environment, like the variable rate application (VRA) technique. Many studies have dealt with the effectiveness of VRA to reduce nitrogen (N) fertilizer, while achieving increased profit and productivity. However, only limited attention was given to VRA’s environmental impact. In this study an International Organization for Standardization (ISO) based Life Cycle Assessment (LCA) performed to identify the environmental effects of N VRA on a small pear orchard, compared to the conventional uniform application. A Cradle to Gate system with a functional unit (FU) of 1 kg of pears was analyzed including high quality primary data of two productive years, including also the non-productive years, as well as all the emissions during pear growing and the supply chains of all inputs, projecting them to the lifespan of the orchard. A methodology was adopted, modelling individual years and averaging over the orchard’s lifetime. Results showed that Climate change, Water scarcity, Fossil fuels and Particulate formation were the most contributing impact categories to the overall environmental impact of the pear orchard lifespan, where climate change and particulates were largely determined by CO2, N2O, and NH3 emissions to the air from fertilizer production and application, and as CO2 from tractor use. Concerning fertilization practice, when VRA was combined with a high yield year, this resulted in significantly reduced environmental impact. LCA evaluating an alternative fertilizer management system in a Greek pear orchard revealed the environmental impact reduction potential of that system.

May smart technologies reduce the environmental impact of nitrogen fertilization? A case study for paddy rice

Precision agriculture is increasingly considered as a powerful solution to mitigate the environmental impact of farming systems. This is because of its ability to use multi-source information in decision support systems to increase the efficiency of farm management. Among the agronomic practices for which precision agriculture concepts were applied in research and operational contexts, variable rate (VR) nitrogen fertilization plays a key role. A promising approach to make quantitative, spatially distributed diagnoses to support VR N fertilization is based on the combined use of remote sensing information and few smart scouting-driven ground estimates to derive maps of nitrogen nutrition index (NNI). In this study, a new smart app for field NNI estimates (PocketNNI) was developed, which can be integrated with remote sensing data. The environmental impact of using PocketNNI and Sentinel 2 products to drive fertilization was evaluated using the Life Cycle Assessment approach and a case study on rice in northern Italy. In particular, the environmental performances of rice fertilized according to VR information derived from the integration of PocketNNI and satellite data was compared with a treatment based on uniform N application. Primary data regarding the cultivation practices and the achieved yields were collected during field tests. Results showed that VR fertilization allowed reducing the environmental impact by 11.0% to 13.6% as compared to uniform N application. For Climate Change, the impact is reduced from 937.3 to 832.7 kg CO₂ eq/t of paddy rice. The highest environmental benefits - mainly due to an improved ratio between grain yield and N fertilizers - were achieved in terms of energy consumption for fertilizer production and of emission of N compounds. Although further validation is needed, these preliminary results are promising and provide a first quantitative indication of the environmental benefits that can be achieved when digital technologies are used to support N fertilization.

Water and nitrogen management effects on semiarid sorghum production and soil trace gas flux under future climate

External inputs to agricultural systems can overcome latent soil and climate constraints on production, while contributing to greenhouse gas emissions from fertilizer and water management inefficiencies. Proper crop selection for a given region can lessen the need for irrigation and timing of N fertilizer application with crop N demand can potentially reduce N₂O emissions and increase N use efficiency while reducing residual soil N and N leaching. However, increased variability in precipitation is an expectation of climate change and makes predicting biomass and gas flux responses to management more challenging. We used the DayCent model to test hypotheses about input intensity controls on sorghum (Sorghum bicolor (L.) Moench) productivity and greenhouse gas emissions in the southwestern United States under future climate. Sorghum had been previously parameterized for DayCent, but an inverse-modeling via parameter estimation method significantly improved model validation to field data. Aboveground production and N₂O flux were more responsive to N additions than irrigation, but simulations with future climate produced lower values for sorghum than current climate. We found positive interactions between irrigation at increased N application for N₂O and CO₂ fluxes. Extremes in sorghum production under future climate were a function of biomass accumulation trajectories related to daily soil water and mineral N. Root C inputs correlated with soil organic C pools, but overall soil C declined at the decadal scale under current weather while modest gains were simulated under future weather. Scaling biomass and N₂O fluxes by unit N and water input revealed that sorghum can be productive without irrigation, and the effect of irrigating crops is difficult to forecast when precipitation is variable within the growing season. These simulation results demonstrate the importance of understanding sorghum production and greenhouse gas emissions at daily scales when assessing annual and decadal-scale management decisions’ effects on aspects of arid and semiarid agroecosystem biogeochemistry.