Precision agriculture: the top new agriculture
September 28, 2022
Precision agriculture (PA), satellite agriculture or site-specific crop management (SSCM) is an agricultural management concept based on observing, measuring, and responding to field and in-field changes in crops. The goal of precision agriculture research is to develop management and decision support systems (DSS) for the entire farm, with the goal of optimizing resources while preserving them and making precise inputs to generate returns.

     Among these many approaches, the phytogeomorphological approach links perennial crop growth stability/characteristics to topological terrain attributes. The interest in phytogeomorphological approaches stems from the fact that geomorphologic components often determine the hydrology of agricultural lands.
    The advent of the Global Positioning System (GPS) and Global Navigation Satellite Systems (GNSS) has made the practice of precision agriculture possible. The ability of farmers and/or researchers to locate their precise position in the field allows for the creation of spatial variability maps of as many variables as can be measured. Sensor arrays mounted on GPS-equipped combines collect a variety of soil-related data, such as: crop yield, topographic features/terrain, organic matter content, moisture content, nitrogen levels, pH, EC (Effective Concentration of Chemicals), Mg (magnesium content), K (potassium content), etc.). These arrays of real-time sensors, which measure states ranging from crop chlorophyll levels as well as crop moisture content, also include multispectral images. These data are used in conjunction with satellite imagery via Variable Rate Technology (VRT) to optimize the allocation of resources, including seeders, sprayers, etc.
    Precision agriculture is also supported by multi-rotor drones like the DJI Phantom, which are relatively inexpensive and can be operated by novices. These agricultural drones can be equipped with hyperspectral or RGB cameras to capture many images of the field that can be processed using photogrammetric methods to create orthophotos and NDVI maps.
I. History.
    PA is an important part of the 3rd wave of modern agricultural revolution. The first agricultural revolution was the mechanization of agriculture, which lasted from 1900 to 1930. During this period, each farmer produced enough food to feed about 26 people.In the 1960s, the second agricultural revolution was the Green Revolution, which triggered new methods of genetic modification, and each farmer fed about 155 people. With the global population projected to reach about 9.6 billion by 2050, food production would have to effectively double from current levels to feed every person on the planet. With the new technological advances of the PA Agricultural Revolution, each farmer will be able to feed 265 people on the same amount of acreage - the third agricultural revolution.
    The first wave of the precision agriculture revolution came in the form of satellite and aerial imagery, weather forecasting, variable speed fertilizer application and crop health indicators. The second wave aggregated big data for more precise planting, topographic mapping and soil data.
    Precision agriculture aims to optimize management in the field by addressing: 1. Crop science: by matching agricultural practices to crop needs (e.g., fertilizer inputs); 2. Environmental protection: by reducing the environmental risks and footprint of agriculture (e.g., limiting nitrogen leaching); and 3. Economics: by improving competitiveness through more efficient practices (e.g., improved management of fertilizer use and other inputs).
     PA also provides a wealth of information for farmers: 1. to build their farm records. 2. to improve decision-making. 3. to promote greater traceability. 4. to enhance the marketing of agricultural products. 5. to improve tenancy arrangements and relationships with landlords. 6. to improve the intrinsic quality of agricultural products (e.g. the protein content of flour wheat). 7. to improve the quality of agricultural products. 8. to improve the quality of agricultural products. 9. to improve the quality of agricultural products (e.g. the protein content of flour wheat).
    Prescribed cultivation. Prescriptive cropping is a farming system that provides data-driven cropping recommendations and allows for variable cropping rates to be determined to suit the varying conditions of individual fields in order to maximize yields. It has been described as "big data for the farm." Global agricultural giants Monsanto, DuPont and others are rolling out the technology in the United States.
    Precision agriculture is often used as a 4-stage process to observe spatial variability:
    1. Data collection. Geo-localization allows farmers to overlay information gathered from soil and residual nitrogen analyses, as well as information about previous crops and soil resistivity. Geo-localization is done in two ways: when a farmer drives a tractor around a field, the site is depicted using an on-board GPS receiver. The field is depicted on a base map derived from aerial or satellite imagery. The base image must have the correct resolution and geometric quality to ensure that the geolocation is sufficiently accurate.
    2. Variability. Intra- and inter-field variability can be caused by many factors. These include climatic conditions (hail, drought, rain, etc.), soils (texture, depth, nitrogen levels), cropping practices (no-till agriculture), weeds and diseases. Permanent indicators - primarily soil indicators - provide farmers with information on key environmental constants. Point indicators enable them to track the status of their crops, i.e., if the crop is suffering from water stress, to see if the condition is developing, nitrogen stress or collapse, if it has been damaged by ice, etc. This information may come from weather stations and other sensors (soil resistivity, visual inspection, satellite imagery, etc.). Soil resistivity measurements combined with soil analysis can measure moisture content. Soil resistivity is also a relatively simple and inexpensive measurement.
    Soil apparent conductivity (ECa) is another major parameter that provides a measure of spatial variation associated with soil physical and chemical properties, and rice soils can be a measure of the suitability of the soil for crop growth, water requirements, and productivity.
    3.Strategies. Using soil maps, farmers can adopt two strategies to adjust field inputs. Predictive approach: analysis based on static indicators (soil, resistivity, field history, etc.) over the crop cycle. Control methods: information from static indicators is updated periodically during the crop cycle: sampling: weighing biomass, measuring leaf chlorophyll content, weighing fruits, etc. remote sensing: measuring temperature parameters (air/soil), humidity (air/soil/leaves), wind or stem coarseness may be due to wireless sensor networks and Internet of Telecommunication (IOT) proxy detection: on-board sensors measure leaf status; this requires the farmer to be on the whole field Driving. Aerial or satellite remote sensing: acquires and processes multispectral images to derive maps of crop biophysical parameters, including disease indicators. Airborne instruments can measure the amount of plant cover and distinguish between crops and weeds. Decisions may be based on decision support models based on big data (crop simulation models and recommendation models), but ultimately, farmers need to decide based on business value and impact on the environment - roles that are taking over through artificial intelligence (AI) systems based on machine learning and artificial neural networks.
     It is important to recognize why precision agriculture technology is being adopted, "For precision agriculture technology to be adopted, farmers must recognize that the technology is useful and easy to use. It may not be sufficient to obtain positive external data on the economic benefits of PA. Technology as a perception of farmers must reflect these economic factors. "
    4. implementation practices
     New information and communication technologies make crop management on farms more operational and easier to implement. The application of crop management decisions requires farm equipment that supports variable rate technology (VRT), such as changing seed densities and variable rate application (VRA) of nitrogen and phytosanitary products. Precision agriculture uses technology on farm equipment (e.g., tractors, sprayers, harvesters, etc.): positioning systems (e.g., GPS receivers that use satellite signals to pinpoint a location on the earth); geographic information systems (GIS), i.e., software that understands all the data that is available; and variable farming equipment (seeders, spreaders).
II Precision agriculture is used around the world
    The concept of PA first appeared in the United States in the early 1980s.In 1985, researchers at the University of Minnesota made changes to lime inputs in crop fields. It was also at this time that the practice of field grid sampling emerged (applying a fixed grid of one sample per hectare). By the late 1980s, this technique was used to derive the first input recommendation maps for fertilizer and pH correction. The use of yield sensors developed from new technology, together with the advent of GPS receivers, has been increasing ever since. Today, such a system covers millions of hectares of farmland.
     In the Midwestern United States, it has less to do with sustainable agriculture and more to do with mainstream farmers who try to maximize their profits by investing only in areas where fertilizer is needed. This practice allows farmers to vary fertilizer rates across their fields based on needs determined by GPS navigation grids or area sampling. Fertilizer is stored in areas where it does not need to be spread, thus optimizing its use.
    Around the world, precision agriculture is growing at different rates. The United States was the first, followed by Canada and Australia. In Europe, the United Kingdom was the first country to follow this path, followed by France, where it first appeared in 1997 - 1998. In Latin America, Argentina is in the leading position, having been introduced in the mid-1990s with the support of the country's Agricultural Technology Institute. Brazil established Embrapa, a state-owned enterprise, to research and develop sustainable agriculture. gps as well as variable speeds
    One-third of the world's population still depends on agriculture for their livelihoods. While more advanced precision agriculture technology requires significant upfront investment, farmers in developing countries are benefiting from mobile technology. The service helps farmers access mobile payments and receipts to improve efficiency. For example, 30,000 farmers in Tanzania use cell phones for contracting and payments, loans, and communication with business organizations.
    The economic and environmental benefits of precision agriculture have also been demonstrated in China, but because the country's agricultural system is characterized by small-scale, family-run farms, China lags behind countries like Europe and the United States. Precision agriculture is lower than in other countries. Therefore, China is working to better introduce precision agriculture technology into the country, reduce some of the risks, and pave the way for the future development of technology for precision agriculture in China.
III. Economic and Environmental Impacts
    As the name suggests, precision agriculture means applying precise and correct amount of inputs such as water, fertilizers, pesticides, etc. to crops at the right time to increase their productivity and maximize yields. Precision farming management practices can significantly avoid wastage and other crop input quantities while increasing yields. As a result, farmers gain a return on their investment by saving on water, pesticide and fertilizer costs.
     A second, larger-scale benefit of precision agriculture involves environmental impact. Applying the right amount of chemicals in the right place and at the right time benefits the crop, the soil, and the groundwater, thus benefiting the entire crop cycle. As a result, precision agriculture has become a cornerstone of sustainable agriculture. This is because it respects the crop, the soil and the farmer. Sustainable agriculture seeks to ensure a continuous supply of food within the ecological, economic and social constraints needed to sustain production over the long term.
    Precision agriculture reduces the pressure of agriculture on the environment by increasing the efficiency of machinery and reducing inputs. For example, the use of remote management devices such as GPS reduces fuel consumption in agriculture, while variable rate applications of nutrients or pesticides can potentially reduce the use of these inputs, resulting in cost savings and less harmful runoff into waterways.
Emerging technologies
Robotics:Self-driving tractors have been around for a while, and John Deere's farm equipment has the autopilot that airplanes have and can work unmanned. Technology is moving toward GPS-programmed unmanned machinery to spread fertilizer or till the ground. Other innovations include solar-powered machines that recognize weeds and kill them with a dose of herbicide or laser precision. Agricultural robots, also known as AgBots, and a number of innovative companies around the world are developing more advanced harvesting robots to recognize ripe fruits, adjust their shape and size, and pick them from branches with precision.
     Drone and Satellite Imagery: The technological advantages of drones and satellites have been a boon to agriculture, allowing for precision cultivation of farmland areas. Drones can capture high-quality images, while satellites can obtain macro data. Light aircraft pilots can combine aerial photography with data from satellite recordings to predict future yields based on current levels of biomass in the field. Numerous images can create contour maps to track the location of water flows, determine variable rate seeds, and create yield maps of areas with more or less efficiency.
IoT:The Internet of Things (IoT) makes data collection and aggregation easier through the use of sensors in conjunction with farm management software. This is known to be inconsistent with the amount of nitrogen, phosphorus and potassium in liquid fertilizers, but farmers can obtain this data by measuring with spectroscopic instruments. Farmers get where cows are already urinating, and by using the IoT and applying fertilizer only where it's needed, they can reduce the amount of fertilizer used by up to 30%. And moisture sensors in the soil can determine the best time and dose to water plants remotely. Irrigation systems linked to the IoT can be programmed to switch which side of the crop needs water based on crop needs and rainfall.
     Innovation is not limited to plants, but can also be used for animal welfare. Cattle can be equipped with internal sensors to track stomach acid and digestive issues. External sensors track movement patterns to determine the health and wellness of the cow, sense if the body is being harmed, and determine the best time to breed. All data from the sensors can be aggregated and analyzed to detect trends and patterns.
    As another example, monitoring technology can be used to make beekeeping more efficient. Honey bees are economically important and provide a vital service to agriculture by pollinating a variety of crops. Monitoring the health of bee colonies through wireless temperature, humidity and CO2 sensors can help improve bee productivity and read in data that could threaten the survival of the entire hive with early warning.
Smartphone AppsSmartphones and tablets are also becoming increasingly popular for use in precision agriculture. Smartphones already come with many useful apps installed, including cameras, microphones, GPS and accelerometers. There are also apps that specialize in a variety of agricultural applications, such as field mapping, tracking animals, and obtaining weather and crop information. They are easy to carry, affordable, and have high computing power.
Machine Learning:machine learning is often used in conjunction with drones, robots, and IoT devices, and it allows for the acquisition of data from each of these data sources. The computer then processes this information and sends the appropriate action back to the device. This allows robots to deliver precise fertilizers to crops through IoT devices, as well as precise amounts of water directly to the soil. The future of agriculture is that by using more machines year after year to engage in learning and data accumulation, making it possible to farm more efficiently and accurately with fewer human resources, ultimately allowing agriculture to report maximized output for humans.