Search for: All records

Precision agriculture (PA) has been defined as a “management strategy that gathers, processes and analyzes temporal, spatial and individual data and combines it with other information to support management decisions according to estimated variability for improved resource use efficiency, productivity, quality, profitability and sustainability of agricultural production.” This definition suggests that because PA should simultaneously increase food production and reduce the environmental footprint, the barriers to adoption of PA should be explored. These barriers include (1) the financial constraints associated with adopting decision support system (DSS); (2) the hesitancy of farmers to change from their trusted advisor to a computer program that often behaves as a black box; (3) questions about data ownership and privacy; and (4) the lack of a trained workforce to provide the necessary training to implement DSSs on individual farms. This paper also discusses the lessons learned from successful and unsuccessful efforts to implement DSSs, the importance of communication with end users during DSS development, and potential career opportunities that DSSs are creating in PA.

 

The use of intelligent decision support systems (DSS) in precision farming provides an opportunity to improve agricultural recommendations and reduce the impacts of agriculture on the environment. Despite the benefits offered by DDS, many farmers remain skeptical of using these hardware and software tools, and their adoption rates have remained low. A survey of 312 South Dakota farmers examined the barriers and opportunities for their engagement with DSS. Exploratory factor analysis was used to analyze 13 Likert scale survey items that probed farmers’ concerns about DSS. Factor loadings indicated that farmers’ concerns are related to high cost, insufficient knowledge, lack of confidence, and cyber security and privacy. A latent profile analysis (LPA) method was used to classify respondents into profiles or groups based on their dimensions of concerns (cost, knowledge, confidence, and security). Results of the LPA revealed that the sample of farmers could be grouped into four distinct profiles that ranged from low to high confidence in the use of DSS for agronomic decision‐making. Giving attention to farmer comfort/concern profiles allows for a more inclusive and better targeted engagement with farmers and potentially increase the adoption of PA. This knowledge can be vital for technology developers, policymakers, and extension services who are keen to promote PA usage among large‐, medium‐, and small‐scale farmers in the United States.

 

Artificial intelligence (AI) represents technologies with human‐like cognitive abilities to learn, perform, and make decisions. AI in precision agriculture (PA) enables farmers and farm managers to deploy highly targeted and precise farming practices based on site‐specific agroclimatic field measurements. The foundational and applied development of AI has matured considerably over the last 30 years. The time is now right to engage seriously with the ethics and responsible practice of AI for the well‐being of farmers and farm managers. In this paper, we identify and discuss both challenges and opportunities for improving farmers’ trust in those providing AI solutions for PA. We highlight that farmers’ trust can be moderated by how the benefits and risks of AI are perceived, shared, and distributed. We propose four recommendations for improving farmers’ trust. First, AI developers should improve model transparency and explainability. Second, clear responsibility and accountability should be assigned to AI decisions. Third, concerns about the fairness of AI need to be overcome to improve human‐machine partnerships in agriculture. Finally, regulation and voluntary compliance of data ownership, privacy, and security are needed, if AI systems are to become accepted and used by farmers.

 

Cover crops improve soil health and reduce the risk of soil erosion. However, their impact on the carbon dioxide equivalence (CO_2e) is unknown. Therefore, the objective of this 2‐yr study was to quantify the effect of cover crop‐induced differences in soil moisture, temperature, organic C, and microorganisms on CO_2e, and to develop machine learning algorithms that predict daily N₂O–N and CO₂–C emissions. The prediction models tested were multiple linear regression, partial least square regression, support vector machine, random forest (RF), and artificial neural network. Models’ performance was accessed using R², RMSE and mean of absolute value of error. Rye (Secale cerealeL.) was dormant seeded in mid‐October, and in the following spring it was terminated at corn's (Zea maysL.) V4 growth stage. Soil temperature, moisture, and N₂O–N and CO₂–C emissions were measured near continuously from soil thaw to harvest in 2019 and 2020. Prior to termination, the cover crop decreased N₂O–N emissions by 34% (p = .05), and over the entire season, N₂O–N emissions from cover crop and no cover crop treatments were similar (p = .71). Based on N₂O–N and CO₂–C emissions over the entire season and the estimated fixed cover crop‐C remaining in the soil, the partial CO_2ewere −1,061 and 496 kg CO_2eha^–1in the cover crop and no cover crop treatments, respectively. The RF algorithm explained more of the daily N₂O–N (73%) and CO₂–C (85%) emissions variability during validation than the other models. Across models, the most important variables were temperature and the amount of cover crop‐C added to the soil.

 

With mounting scientific evidence demonstrating adverse global climate change (GCC) impacts to water quality, water quality policies, such as the Total Maximum Daily Loads (TMDLs) under the U.S. Clean Water Act, have begun accounting for GCC effects in setting nutrient load‐reduction policy targets. These targets generally require nutrient reductions for attaining prescribed water quality standards (WQS) by setting safe levels of nutrient concentrations that curtail potentially harmful cyanobacteria blooms (CyanoHABs). While some governments require WQS to consider climate change, few tools are available to model the complex interactions between climate change and benthic legacy nutrients. We present a novel process‐based integrated assessment model (IAM) that examines the extent to which synergistic relationships between GCC and legacy Phosphorus release could compromise the ability of water quality policies to attain established WQS. The IAM is calibrated for simulating the eutrophic Missisquoi Bay and watershed in Lake Champlain (2001–2050). Water quality impacts of seven P‐reduction scenarios, including the 64.3% reduction specified under the current TMDL, were examined under 17 GCC scenarios. The TMDL WQS of 0.025 mg/L total phosphorus is unlikely to be met by 2035 under the mandated 64.3% reduction for all GCC scenarios. IAM simulations show that the frequency and severity of summer CyanoHABs increased or minimally decreased under most climate and nutrient reduction scenarios. By harnessing IAMs that couple complex process‐based simulation models, the management of water quality in freshwater lakes can become more adaptive through explicit accounting of GCC effects on both the external and internal sources of nutrients.

 

Abstract Because the manual counting of soybean ( Glycine max ) plants, pods, and seeds/pods is unsuitable for soybean yield predictions, alternative methods are desired. Therefore, the objective was to determine if satellite remote sensing − based artificial intelligence (AI) models could be used to predict soybean yield. In the study, multiple remote sensing − based AI models were developed for soybean growth stage ranging from VE/VC (plant emergence) to R6/R7 (full seed to beginning maturity). The ability of the Deep Neural Network (DNN), Support Vector Machine (SVM), Random Forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO), and AdaBoost to predict soybean yield, based on blue, green, red, and near infrared reflectance data collected by the PlanetScope satellite at 6 growth stages, was determined. Remote sensing and soybean yield monitor data from 3 different fields in two years (2019 and 2021) were aggregated into 24,282 grid cells that had the dimensions of 10 by 10m. A comparison across models showed that the DNN outperformed the other models. Moreover, as crops matured from VE/VC to R4/R5, the R 2 value of the models increased from 0.26 to over 0.70. These findings indicate that remote sensing data collected at different growth stages can be combined for soybean yield predictions. Moreover, additional work needs to be conducted to assess the model's ability to predict soybean yield with vegetation indices (VI) data for fields not used to train the model. This article is protected by copyright. All rights reserved 

Highlights Changes to soil properties and precipitation scenarios significantly affect the water balance in agro-hydrology. SPAW model is sensitive to simulated runoff and infiltration, but it has limitations in responding to soil compaction and organic matter change. Increasing organic matter (1% to 5%) did not significantly affect runoff or infiltration in silty and sandy loam soil. Low precipitation generates significantly lower runoff (%) and higher infiltration. Abstract. Agricultural practices can change soil properties and the amount of runoff generated from a landscape. Modeling results could be significantly different than expected if the web soil survey or other commonly used remote sensing applications are used as model inputs without site verification. This study assessed the applicability and sensitivity of the Soil-Plant-Air-Water (SPAW) Model for simulating the runoff (%) and infiltration (%) components of the water balance for various soil physical properties, cover crop, and weather variables. Soil profiles in 135 combinations were developed with three soil classes (sandy loam, silt loam, and clay), five organic matter levels (1%, 2%, 3%, 4%, and 5%), three levels of compaction (low, medium, and high), and three topsoil layer thicknesses (7.6 cm, 11.4 cm, and 15 cm). Also, three cover crop treatments were simulated by modifying surface cover and evapotranspiration during the non-growing season. Finally, two precipitation regimes were considered (Iowa City, IA, as high precipitation and Brookings, SD, as low precipitation) to simulate runoff and infiltration. In total, 810 scenarios were run, resulting in over 300 million data points. This study confirmed that soil texture, bulk density, and topsoil thickness significantly (p<0.01) influence runoff generation and infiltration percentage based on the water balance criterion. Interestingly, the SPAW model had no significant response on runoff (%) and infiltration (%) to organic matter levels changing from 1% to 5%. This simulation demonstrates that runoff estimations can be significantly influenced by soil properties that can change due to agricultural conservation practices (ACPs) or, conversely, by compaction events. Inputs to models must account for these changes rather than relying only on historical or remote sensing inputs. Keywords: Agricultural conservation practices, Conservation agriculture, Field hydrology, Infiltration, Runoff, SPAW.