- Data Categories
Agriculture Data 
B2B Data 
Biometric Data 
Company Data 
Conservation Data 
Demographic Data 
Economic Data 
Environmental Data 
Geospatial Data 
Healthcare Data 
Individual Data 
Industry-Specific Data 
Internet of Things (IoT) Data 
Legal and IP Data 
People and Employment Data 
Political Data 
Psychology Data 
Real Estate Data 
Retail & Commerce Data 
Social Data 
Space Exploration Data 
Sports & Entertainment Data 
Web Data
- Data Categories
- Agriculture Data
- B2B Data
- Biometric Data
- Company Data
- Conservation Data
- Demographic Data
- Economic Data
- Environmental Data
- Geospatial Data
- Healthcare Data
- Individual Data
- Industry-Specific Data
- Internet of Things (IoT) Data
- Legal and IP Data
- People and Employment Data
- Political Data
- Psychology Data
- Real Estate Data
- Retail & Commerce Data
- Social Data
- Space Exploration Data
- Sports & Entertainment Data
- Web Data
Smart Farming
What is Smart Farming Data?
Smart farming refers to the use of connected technology and artificial intelligence in the field of agriculture. It is also referred to as smart agriculture, agritech, agrotech, or even agro technology. However, the terms agritech and agrotech include the fields of horticulture and aquaculture.
Why Is It Important to Have a Smart Farming Model?
There are few things in the world as important—or as risky—as growing food to feed people. Therefore, farmers should use the latest technologies and machine learning programs to ensure consistently productive yields.
Smart farming can also help alleviate poverty while improving sustainability efforts. This is especially so when open-source data are made available to farmers in developing countries.
What Internal Data Should I Have for a Good Smart Farming Model?
The line between internal data and external data can become blurred. For instance, while employee, equipment, and seed type data are clearly internal, the farmland itself might not be.
Put another way, the land belongs to the farmer but its soil quality, growing season, or biome might be classified as external data.
What External Data Is Essential for a Good Model?
In addition to climate and weather, essential external data for a smart farming system includes crop and livestock threat monitoring—for example, disease outbreaks.
What External Data May Prove Useful for a Good Model?
Additional external data includes supply chain data and market trends. Supply chain problems, for instance, affect the condition of the food when it reaches market, which affects the farm’s profitability. Meanwhile, market trends could indicate to the farmer which crops or farming techniques (such as organic or pesticide-free farming practices) he or she should consider taking on in the future.
What Are the Main Challenges of this Use Case?
Despite the fact that smart farming technology allows for 24/7 crop and livestock monitoring and predictive analytics, agriculture remains a very risky business. Natural disasters threaten the farm and ranch as well as the supply chain, as do political developments (e.g., embargoes and tariffs). Farmers much purchase and maintain equipment. And larger enterprises have stakeholders to please, who may be more susceptible to market trends than the farmers themselves.
Interesting Case Studies and Blogs to Look Into
Science Direct: Big Data in Smart Farming – A review
Statista: Smart Agriculture
Tangible Examples of Impact
A smart farming startup has launched the third element in its robot system for pesticide-free agriculture, an AI-based system called Wilma.
Wilma, developed by the Small Robot Company, provides ‘per plant intelligence’, using precise information gleaned by Tom, a scouting robot, on the health of the plant. If Wilma identifies the plant as a weed then Dick – the world’s first non-chemical robotic weeder – is dispatched to zap it.
eeNews Europe: AI for pesticide-free smart farming weed removal
Connected Categories
Connected Datasets
Airborne magnetic and radiometric survey, southeast Missouri and western Illinois, 2018-2019
This publication provides digital flight line data for a high-resolution horizontal magnetic gradient and radiometric survey over an area of southeast Missouri and western Illinois. The survey represents the first airborne geophysical survey conducted as part of the U.S. Geological Survey (USGS) Earth Mapping Resource Initiative (Earth MRI) effort (Day, 2019). Earth MRI is a cooperative effort between the USGS, the Association of American State Geologists, and other Federal, State, and private sector organizations to improve our knowledge of the geologic framework of the United States. Data for this survey were collected by Terraquest, Ltd. under contract with the USGS using a fixed wing aircraft with magnetometers mounted in the tail stinger and each wing tip pod and a fully calibrated gamma ray spectrometer. The
Application of fertilizer phosphorus to farm land in the United States Pacific Northwest for 2002
This spatial data set was created by the U.S. Geological Survey (USGS) to represent the amount of fertilizer phosphorus that was applied to farm land in the Pacific Northwest region of the United States (Hydro Region 17, Major River Basin 7 (MRB7)) during 2002.
Application of fertilizer phosphorus to nonfarm land in the United States Pacific Northwest for 2002
This spatial data set was created by the U.S. Geological Survey (USGS) to represent the amount of fertilizer phosphorus that was applied to nonfarm land in the Pacific Northwest region of the United States (Hydro Region 17, Major River Basin 7 (MRB7)) during 2002.
Application of fertilizer nitrogen to nonfarm land in the United States Pacific Northwest for 2002
This spatial data set was created by the U.S. Geological Survey (USGS) to represent the amount of fertilizer nitrogen that was applied to nonfarm land in the Pacific Northwest region of the United States (Hydro Region 17, Major River Basin 7 (MRB7)) during 2002.
Vulnerability of shallow ground water and drinking-water wells to nitrate in the United States: Model of predicted nitrate concentration in U.S. ground water used for drinking (simulation depth 50 meters) — Input data set for confined manure (gwava-dw_conf)
This data set represents the average annual nitrogen input from confined animal manure, 1992 and 1997, in kilograms per hectare, in the conterminous United States. The data set was used as an input data layer for a national model to predict nitrate concentration in ground water used for drinking. Nolan and Hitt (2006) developed two national models to predict contamination of ground water by nonpoint sources of nitrate. The nonlinear approach to national-scale Ground-WAter Vulnerability Assessment (GWAVA) uses components representing nitrogen (N) sources, transport, and attenuation. One model (GWAVA-S) predicts nitrate contamination of shallow (typically less than 5 meters deep), recently recharged ground water, which may or may not be used for drinking. The other (GWAVA-DW) predicts ambient nitrate concentration in deeper supplies used for