(FREE) UPSC Current Affairs 2024 PDF

(The Gist of Kurukshetra) Smart Agriculture INDIA [JUNE-2020]

(The Gist of Kurukshetra) Smart Agriculture

INDIA [JUNE-2020]

Smart Agriculture

Introduction:

According to the Food and Agriculture Organization (FAO), globally irrigated agriculture represents 20 percent of the total cultivated land, but contributes only 40 percent of the total food produced worldwide.
Water is a critical resource in agriculture and higher variations in usage can have adverse consequences on crop yields and soil health. Presently, irrigation water-use accounts for 80 percent of the available water.
The FAO estimates that over the last century the global water withdrawal grew 1.7 times faster than the population, which aggravates the concern over the sustainability of water use as the demand for agricultural, industrial and domestic uses continues to increase.
Improving agricultural productivity, while conserving and enhancing natural resources, such as water, is an essential requirement for farmers to increase global food supplies on a sustainable basis.
The role of smallholder farmers and their families in increasing agricultural productivity growth sustainably will be crucial because most of the world’s agriculture is carried out by millions of small farmers who produce a large share of the world’s food and support their households.
We have to realise the importance of judicious use of water by remembering that it takes between one and three tonnes of water to grow one kg of cereal. It is estimated that irrigation requirements has to be lowered to the level of 68 percent of the total demand by 2050.

Transformative Discoveries for Smart Agriculture:

There is a basket of technologies and innovations that enable production technology of smart agriculture. The concept, science and applications of such innovations are described below:

Internet of Things (IoT):

IoT is described as a network of physical objects. These can be “things” that can be embedded with technologies, software or sensors which further helps in connecting or the exchange of data with other devices or systems via the internet or vice versa. In 2016, more than 5.5 million new “things” got connected every day, thus creating a huge scope for the Internet of Things. There are over 8.3 billion IoT devices connected today.

Artificial Intelligence (AI):

It is the science of instilling intelligence in machines so that they are capable of doing tasks that traditionally required the human mind. The term AI is commonly used when a machine mimics cognitive functions such as planning, learning, reasoning, problem solving, knowledge representation, perception, motion, manipulation, social intelligence, and creativity.
AI combines automation, robotics, and computer vision. Advances in statistics, faster computers, and access to large amounts of data have augmented the advances in AI, particularly in the field of Machine Learning where significant progress has been made in the areas of image and pattern recognition, natural language understanding, and robotics.
Integration of AI and IoT devices further improves the growing and selling processes via predictive analytics. These programmes will help farmers determine which crops to grow and anticipate potential threats by combining historical information about weather patterns and crop performance with real-time data.

Blockchain:

It is a recent technological advancement with potential for addressing the challenge of creating a more transparent, authentic, and trustworthy digital record of the journey that food and other physical products take across the supply chain.
Blockchain works by mapping data and providing it to users along the value chain simply by scanning a barcode. These barcodes are applied and linked throughout the value chain automatically by grading and sorting robotics. This information not only provides the consumer with transparency, but also reduces risks for producers at the same time making available a cost-effective supply chain analysis to optimise profits.
When blockchain is integrated with IoT, it creates an immutable supply chain, ensuring that buyers are getting an authentic product that has not been damaged along the way. These technologies can also verify whether a product that contains hazardous materials has been disposed of correctly and safely.

Robotics:

Powered with advanced AI technology, robots will soon play a defining role in agriculture. Advanced computer vision is also transforming the way drones operate. Drones with AI-enabled vision processing capabilities are being used to assess the real situation on the condition of crops on ground.
Autonomous drones and the data they provide can help in crop monitoring, soil assessment, plant emergence and population, fertility, crop protection, crop insurance reporting in real time, irrigation and drainage planning and harvest planning.

Autonomous Swarms:

Autonomous swarms combine the technology of swarm robotics with a blockchain-based backend. Swarm robotics involves multiple copies of the same robot, working independently in parallel to achieve a goal too large for any one robot to accomplish.
By leveraging the benefits of both swarm robotics and Blockchain, pesticide and fertilizer can be applied more sparingly and planting and harvesting can be done with individual attention to each plant, an impossible task with large-scale machinery. The new approach produces greater yields at reduced cost, while raising the quality of the crop.

Artificial Intelligence of Things (AIoT):

Individually, the Internet of Things (IoT) and Artificial Intelligence (AI) are powerful technologies. AIoT is a combination of AI and IoT. AI can complete a set of tasks or learn from data in a way that seems intelligent.
Devices empowered with the combination of AI and IoT can analyse data and make decisions and act on that data without involvement by humans.

Big Data:

It is a combination of technology and analytics that can collect and compile novel data and process it in a more useful and timely way to assist decision making. Data mining is the computing process of discovering patterns in large data sets involving methods at the intersection of artificial intelligence, machine learning statistics and database system.
Big Data and analytics have the potential to add value across each step and can streamline food processing value chains such as selection of right agri-inputs, monitoring soil moisture, tracking prices of market, controlling irrigations, finding the right selling point and getting the right price.

Focus on Higher Water-use Efficiency

Since the advent of the Green Revolution, irrigation has been the main intervention to assure the reliability and productivity of cropping in India and has played a significant role in national food security. The area equipped for irrigation has grown enormously over the past five decades in India.
The country records only 38 percent water use efficiency in the field of agriculture and much needs to be done to improve it. Conventional surface irrigation provides 60–70 percent efficiency, whereas, higher efficiency of up to 70–80 percent with sprinkler and 90 percent with drip irrigation systems can be achieved. Implementation of smart irrigation by looking into the evapotranspiration parameter of plants to optimise the irrigation cycle is well in play.
The use of soil moisture content and temperature sensors are widely prevalent in scheduling irrigation. Drones equipped with hyperspectral, multispectral, or thermal sensors are able to identify areas that require changes in irrigation. Once crops have started growing, these sensors are able to calculate their vegetation index and indicator of health through AI, by measuring the crop’s heat signature.
Analog irrigation systems have been used in commercial agriculture for some time and they operate on pre-programmed schedules and timers.
As we do not take in to account the data on daily weather conditions, this often leaves farmers unprepared for sudden weather changes and can lead to significant overwatering and waste. Smart irrigation systems are more inclusive to such risks and are equipped with self-governing capabilities that result in more precise watering schedules that reflect the actual conditions of the grow site. Smart irrigation comprises specialised hardware devices, software and services used to obtain real time data to help farmers make effective decisions pertaining to their farms.
The combination of IoT and AI technologies, such as Machine Learning, computer vision and predictive analytics, further allow farmers to analyse real-time data of weather conditions, temperature, soil moisture and plant health. According to the Alliance for Water Efficiency, most smart irrigation technologies fall under two classifications:
Sensor-based Control: This method leverages real-time measurements from locally installed sensors to automatically adjust irrigation timing to the exact temperature, rainfall, humidity and soil moisture present in a given environment. This data is also supplemented with historic weather information to ensure farmers are able to anticipate unfavourable conditions.
Signal-based Control: Unlike sensor-based controls, these smart irrigation systems rely on weather updates transmitted by radio, telephone or web-based applications. These signals are typically sent from local weather stations to update the “evapotranspiration rate” of the irrigation controller.

Need for Water Accounting:

Water accounting includes sophisticated approaches to demand forecasting on the basis of demographic change, urbanisation, industrialisation and energy production. Water accounting is an essential underpinning to transparent and effective water allocation systems. Such systems have been developed in some countries (e.g. Australia, China, France, Iran, and the US) with varying levels of sophistication and effectiveness. In China, water is allocated to different sectors (e.g. agriculture, urban and rural domestic, sanitation, industry, environment) within a limit on total water use at the national level and in each major river basin.
Water accounts are created to assess the volume of water resources available at basin and subsidiary levels, to incorporate long-term inter annual variability in rainfall and weather, and to estimate water availability. Available water includes water stored in dams/reservoirs and underground. The accounts are updated through the year and reassessed at the beginning of each “water year”.
Water accounts are typically constructed on the basis of catchment-scale hydrologic modelling, required data on rainfall, evaporation and transpiration and stream flow over the entire landscape.

Initiatives of Smart Agriculture:

NITI Aayog came up with a National Strategy for Artificial Intelligence in India, which is aimed at focusing on economic growth and social inclusion.
The Government signed an MOU with IBM to use AI to secure the farming capabilities of Indian farmers. The pilot study will be conducted in states like Madhya Pradesh, Gujarat and Maharashtra. After the pilot study, IBM’s Watson decision platform will provide a farm-level solution for improving the agriculture sector.
It will provide weather forecast and soil moisture information to farmers to take pre-informed decisions regarding better management of water, soil and crop.
This initiative was aimed at improving the future of farming by harnessing multiple data points and combine predictive analytics, AI, satellite data, and IoT sensors to give farmers insights on ploughing, choosing crops, spraying pesticides, and harvesting.
In a bid to push innovative technologies in agriculture sector, the government has also launched AGRI-UDAAN to mentor 40 agricultural start-ups from cities like Chandigarh, Ahmedabad, Pune, Bengaluru, Kolkata and Hyderabad, and enable them to connect with potential investors.
Maha Agri Tech Project in Maharashtra is another such project which seeks to use innovative technologies to address various risks related to cultivation such as poor rains, pest attacks, etc., and to accurately predict crop yielding.
The project will also use this data to inform farmers about several policy requirements including pricing, warehousing and crop insurance. The first phase of the project uses satellite images and the data analysis done by Maharashtra Remote Sensing Application Centre (MRSAC) and the National Remote Sensing Centre (NRSC) to assess the area of land, and the conditions of select crops in select talukas.
However, the second phase includes an analysis of the data collected to build a seamless framework for agriculture modelling and a geospatial database of soil nutrients, rainfall, and moisture stress to facilitate location-specific advisories to farmers.
Smart agriculture has the potential to double the food production with lesser impact on climate change. Further, it can reduce the losses and wastage. It is estimated that the IoT has the potential to increase agricultural productivity by 70 percent by 2050.6
There is a need to develop an infrastructure in our agricultural institutions to have scientific understanding for such technologies so that the farmers can be trained to use of such technologies and equipments in the field.
There is a need for convergence of available institutional resources in the country.
We have best technology institutions of the world like Indian Institutes of Technology, National Institutes of Technology, Indian Institute of Science, etc.
Our immediate need is to rope in these institutions with our top agricultural intuitions for testing and validation of the suitable technologies in commercially important crops in different parts of the country.
In the long run, there should be a collaboration in these technology and agricultural institutions for the development of such technologies for sustaining smart agriculture in the country