Opportunities and Challenges for Big Data in Agricultural and Environmental Analysis

Weersink, Alfons; Fraser, Evan D. G.; Pannell, David J.; Duncan, Emily; Rotz, Sarah

doi:10.1146/annurev-resource-100516-053654

Cited by 232 publications

(185 citation statements)

References 75 publications

(63 reference statements)

Supporting

Mentioning

144

Contrasting

Unclassified

Order By: Relevance

“…The data interpretation must reach the farmers with decision support tools. [53] Research scholars are trying to develop a large scale data analytics tool using machine learning opportunity. Agricultural data is heterogeneous from different repositories (statistical, images, unstructured data, etc) could have enormous significance for a learning task.…”

Section: Machine Learning For Big Data Analysismentioning

confidence: 99%

“…Transferring of data from fields located in the rural area to the centralized servers requires internet connectivity. [53] In India, internet connectivity is yet to be established in rural areas. The correlation and integration of data from various sources with the different format is the challenge to derive required decisions out of it.…”

Section: Challengesmentioning

confidence: 99%

“…Farmers are unable to sell their harvest when they don't get the yield as planned qualitatively and quantitatively. This demands focused attention on adapting modern tools in farming and intuitive planning of farm management strategies with analysis of historical data to substantiate the decisions.The digital revolution in agriculture is focused on low-cost data collection of soil conditions, weather station and data collected by the satellites [53]. The farming methods are now supported by innovative digital technologies such as rain gauge, soil sensors, moisture sensors, thermostats with assistance from the Internet of things (IoT).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Role of Big Data in Agriculture

J*¹,

Indiramma²

2019

IJITEE

View full text Add to dashboard Cite

Big Data analytics in the agricultural sector has huge potential to cater to requirements of food production. This review highlights the role of Big Data in pertinent data acquisition from factors affecting the agriculture such as weather, soil, diseases, remote sensing and the prospects of agricultural data analysis towards smart farming. Incorporating modern technologies in farming practices continuously monitor the environment, thus producing large quantity of data. Hence there arises the need for advanced practical and systematic strategies to correlate the different factors driving the agriculture to derive valuable information out of it. Big Data can be a promising aspect for the future of food production and sustainability of agriculture. Leveraging big data in the agricultural sector can provide insights in farming practices, helps in making real-time decisions and motivates in incorporating new methods of farming operations. The main objective of this paper is to provide insights into different factors that contribute to making timely recommendations to farmers with regard to smart agricultural techniques.

show abstract

Section: Machine Learning For Big Data Analysismentioning

confidence: 99%

Section: Challengesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Role of Big Data in Agriculture

J*¹,

Indiramma²

2019

IJITEE

View full text Add to dashboard Cite

show abstract

“…The digital revolution, allowing the rate of fertilizer to vary spatially across the field in contrast to the traditional approach of a single uniform rate, has the potential to increase net returns while concurrently reducing the sector's environmental impact (Weersink et al . ). However, uptake has been unexpectedly slow, so the application provides an opportunity to assess the range of factors affecting adoption (Mitchell et al .…”

Section: Introductionmentioning

confidence: 97%

Limits to Profit Maximization as a Guide to Behavior Change

Weersink¹,

Fulton²

2020

Applied Eco Perspectives Pol

Self Cite

View full text Add to dashboard Cite

Economists have long been interested in why farmers decide to adopt new technologies. Modeling decision making requires modeling behavior; the key behavioral assumption is profit maximization. In addition, most empirical studies assume a binary decision—adopt or not. This paper argues that adoption should be understood as a process with multiple stages in which the final decision to use the new technology only occurs if the previous stages are completed. While profit considerations are clearly important, particularly in the later stages of the process, they need to be supplemented with other social and cognitive considerations, particularly in the early stages. Understood this way, profit maximization assumptions can provide predictions for the upper or lower bounds of adoption. The adoption rate suggested by profit maximization will be an upper bound if noneconomic factors are expected to either slow down or deter adoption, while that rate will be a lower bound if noneconomic factors are expected to encourage adoption. To capture these elements, econometric models need to pay attention to the timing of decisions and use techniques that condition later‐stage decisions on previous stage outcomes. In addition, the paper suggests the use of expert systems that have economic, learning and social aspects explicitly built into them would be valuable.

show abstract

“…Biologicals such as plant-beneficial microbes are being used for plant disease control, plant growth promotion, and as biological fertilizers to enhance availability of nutrients such as nitrogen, and phosphate to plants (Finkel et al, 2017;Backer et al, 2018). Other efforts include reducing tillage to build soil health and decreasing inputs of synthetic fertilizers and pesticides through big-data driven precision agriculture (Gebbers and Adamchuk, 2010;Mattoo and Teasdale, 2010;Balafoutis et al, 2017;Roberts and Mattoo, 2018;Weersink et al, 2018). A growing body of evidence indicates that crop management strategies can impact crop nutritional quality (Zhu et al, 2007;Hirschi, 2009;Fatima et al, 2016;Vasconcelos et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

Sustainable Crop Production Systems and Human Nutrition

Roberts

Mattoo

2019

Front. Sustain. Food Syst.

View full text Add to dashboard Cite

There is a pressing need for redesigning agriculture to achieve sustainability and for utilizing modern genetic tools, including genetic engineering, to add nutritional value to crops for the benefit of the diverse human population. Collectively, plant foods contain most minerals, macronutrients (calories), and micronutrients essential for human nutrition. These plant foods also contain a range of bioactive compounds that can play important roles in the prevention of chronic diseases including heart disease, cancer, stroke, diabetes, Alzheimer's, cataracts, and age-related functional decline. However, these bioactive nutrients are often present at marginal concentrations in edible plant tissues in regard to human nutrition/prevention of disease. The quantity of these nutrients in edible plant tissues is primarily dependent on crop genetics and regulated by complex and overlapping mechanisms in response to developmental and environmental cues. Environmental cues are naturally occurring-temperature, light intensity, and other stressors, or result from crop production system components-fertilizer, tillage operations, etc. One strategy for sustainable, next-generation crop development is to design cropping systems that have minimal or lesser impact on the environment and to use genetic approaches to enhance crop nutritional content. This strategy is appealing since crop genetics is the primary driver of plant nutrient content and because purely managing crop production fields to optimize crop nutrient content is extremely challenging if not impossible. As an example we present the development of a next-generation sustainable tomato production system with beneficial impacts on tomato physiology and nutritional quality of the tomato fruit. Our analysis of the metabolomes of tomato cultivars in this and other cropping systems highlights the need for robust cultivars that consistently express nutritional and other desirable traits across cropping systems and under differing environmental conditions.

show abstract

Opportunities and Challenges for Big Data in Agricultural and Environmental Analysis

Cited by 232 publications

References 75 publications

Role of Big Data in Agriculture

Role of Big Data in Agriculture

Limits to Profit Maximization as a Guide to Behavior Change

Sustainable Crop Production Systems and Human Nutrition

Contact Info

Product

Resources

About