CropIn Technologies

Smart Farming

Smart Farming is focussed on the use of data acquired through various sources (historical, geographical and instrumental) in the management of farm activities. Technologically advanced doesn’t essentially mean that it is a smart system. Smart systems differentiate themselves through their ability to record the data and make sense out of it. Smart farming employs hardware (IoT) and software (SaaS) to capture the data and give actionable insights to manage all the operations on the farm, both pre and post harvest. The data is organized, accessible all the time and full of data on every aspect of finance and field operations that can be monitored from anywhere in the world.

DIFFERENCES BETWEEN TRADITIONAL AND SMART FARMING

Traditional Farming

Same set of practices for cultivation of a crop throughout the region

Manual maintenance of all the field and finance data separately leading to errors

Application of fertilizers and pesticides throughout the field

Geo-tagging and zone detection not possible

No way to predict weather

Smart Farming

Each farm is analysed to see the suitable crops and water requirements for optimization

Early detection and application at the affected region only, saving costs

Field and finance data available in same place showing the profilts, yields and patterns with simple reports.

Satellite imagery detects the different zones in farms

Weather analysis and prediction

HOW AUTOMATION AND ROBOTICS HELP?

IoT (Internet of Things) in agriculture involves sensors, drones and robots connected through internet which function automatically and semi automatically performing operations and gathering data aimed at increasing efficiency and predictability. With increasing demands and shortage of labor across the globe, agriculture automation and robots or commonly known as Agribots are starting to gain attention among farmers. Crop production decreased by an estimated 213 crores approx ($3.1 billion) a year due to labor shortages in the USA alone. Recent advancements in sensors and AI technology that lets machines to train on their surroundings has made agrobots more notable. The world is in the early stages of an ag robotics revolution with most of the products still in trial phases and R&D mode.

Semi automatic robots with arms can detect weeds and spray pesticides in the affected plants, saving up the plants as well as over all pesticide costs. These robots can also be used in harvesting and lifting. Heavy farming vehicles can also be navigated from the comfort of homes through phone screens to perform tasks and GPS can track their positions at every time.

Drones equipped with sensors and cameras are used for imaging, mapping and surveying the farms. They can be remotely controlled or they can fly automatically through software-controlled flight plans in their embedded systems, working in coordination with sensors and GPS. From the drone data, insights can be drawn regarding crop health, irrigation, spraying, planting, soil and field, plant counting and yield prediction and much more.

IoT based remote sensing utilizes sensors placed along the farms like weather stations for gathering data which is transmitted to analytical tool for analysis. They monitor the crops for changes in light, humidity, temperature, shape and size. The data collected by sensors in terms of humidity, temperature, moisture precipitation and dew detection helps in determining the weather pattern in farms so that cultivation is done for suitable crops. The analysis of quality of soil helps in determining the nutrient value and drier areas of farms, soil drainage capacity or acidity, which allows to adjust the amount of water needed for irrigation and the opt most beneficial type of cultivation. Computer imaging involves the use of sensor cameras installed at different corners of the farm or drones equipped with cameras to produce images which undergo digital image processing. The images are used for quality control, disease detection, sorting and grading yield and irrigation monitoring through Image processing combined with machine learning which uses images from database to compare with images of crops to determine the size, shape, color and growth therefore controlling the quality.

ROLE OF SAAS-BASED CLOUD SOFTWARE IN SMART FARMING

Cloud based software is used for the management of financial and field activities of farms. Prior to computers, farmers maintained data manually by keeping lengthy records on papers. This method was prone to human calculation errors. After the computer boom in the 1980s, it was not long before finance softwares such as Money Counts came to market. They used spreadsheets to maintain the financial data. The biggest challenge that farmers faced was the inability to manage field data. These softwares were used to maintain finance data only. Around mid 2000s, satellite image use with tools like Raven Receiver for field zone tracking became widely used. Farmers had to implement and coordinate different tools to manage complete farm operation. With constant improvements through the years Agritech SaaS has become all in one tool for management of all these activities and more at one place through a single tool. A good example would be CropIn, that is working with Government of Karnataka and leading multinational agri corporations utilizing data analytics and satellite imagery to collect, analyze data and manage all the activities from farm to fork.

Data Collection

One of the biggest applications of cloud software in agriculture is for data collection and retrievement. Cloud software store tonnes of data relating to weather cycles, crop patterns, soil quality, harvesting and satellite imagery to provide insights with sharp accuracy and speed. All the data related to farm is stored in cloud and hence readily accessible. So if in future, crops are infected with the same symptoms as 10 years ago, the data can be used to find the remedy used at that time.

Data Processing/Analysis

Database management in cloud software tie up all the loose ends of every type of data available with respect to farm to enable higher level of decision-making. Meteorological data, market data, farm data, GIS and water availability - all the data from past and present is analysed thoroughly before giving optimum value of seeding, water and pesticide requirements for a farm. The systems also have an alert system whenever discrepancies in crop growth are detected. Hence these systems work efficiently in case of pest attack informing farmers with actionable data.

Data Storage and Dissemination

Data storage is the backbone of predictive analysis. Earlier the data storage was hardware based, hence hardware needed to be carefully maintained and stored. Loss of hardware meant the data was gone forever. Nowadays the agritech systems are cloud based, which means that one need not invest in purchase and maintenance of hardware. All the data is available all the time and can be accessed through phone, PCs and tablets. Data storage is significant also in accurate analysis. The more data is available relating to farms, the more accurate detection of weather phenomena, pests, crop yield and profits will be.

Applications of Cloud-based Software

Cloud-based software finds applications with

Food Production Companies - Output Predictability

Financial Lending Companies - Risk Management

Insurance Providers - Risk Coverage

Agri Input Companies - Production Forecast

Seed Production Companies - Quality Maximisation

Government Advisories - Output Predictability & Sustainability

SUMMARY

Smart Farming focuses on application of acquired data and combining it from various data sources to show the bigger picture to manage all the activities of the farm. Smart farming is a big leap from traditional farming as it brings certainty and predictability to table. Robotics, automation and cloud software systems are tools for smart farming. Robotics, drones and sensor equipment placed throughout the farms can collect data and this data is processed to produce farm insights. Cloud based software can be used to collect the data on farm and process the data relative to weather patterns, yields, irrigation and satellite imagery, and off farm - such as markets and dealer availability to perform predictive analysis. Cloud based software finds the applications for farmers, banks, food processing companies, insurance providers, seed production and government.

FAQ

Has IoT or Cloud-based SaaS (Software as a Service) solutions been applied for ‘smarter agriculture’ scenarios in agriculture dominated developing economies?

Although IoT is still at a nascent stage, the governments of agriculture dominant developing economies do invest in cutting-edge technologies like IoT, AI and Machine Learning for making smarter agriculture solutions. In agri-based economies like India, the implementation of IoT in agriculture has its own set of unique benefits and challenges.

Firstly, the farmers fear upgrading to agtech as they lack the knowledge about the applicability of technology in agriculture. Besides this, the sensors, robots and drones that are used in the development of IoT solutions are expensive and high maintenance and require technically trained labor for operating them. The data collected needs to be analysed - this can be done by taking them to a lab or by using instruments on farm. Also a variety of sensors are required for collecting data on different parameters which needs to be analysed separately, hence making them high-ticket budget items. Therefore, the designed solutions must be cost-effective and highly scalable, considering the various farm sizes.

What are the benefits of smart farming using SaaS solutions?

Readily available and accessible management through smartphones, tablets and PCs

Alert Log & Management (pest infestation, diseases etc.)

Incorporates end-to-end solutions from farm to fork traceability

Robust & flexible system for Farm Management

Satellite and weather input based advisory

Higher yield as inputs are optimized and constantly monitored

Traceability & Output Predictability

Crop reports & insights – easy reporting on-the-go

Better quality due to compliance of food standards and nutrition tracking

Accountable & Efficient Operations

Geo tagging for accountability & accurate predictability

Less waste due to customized practices accounting for precise application of resources and thus reduction in production costs

Standard package of practices

Adherence to Compliance & Certification

As a multinational farming company, it is only natural that we switch to smart farming to optimize productivity. What are the differences between IoT and SaaS solutions that we should consider before investing in one?

SaaS

High skilled labor not required

No equipment required on farms

Labor logs and chemical usage data available

No physical equipment required to be placed on farms.

No hardware maintenance costs, Insights are accessible on laptop or PC screens and data stored in clouds

High resolution satellite images for monitoring and weather analysis

One stop solution for managing all the operations pre and post harvest

Very scalable for multi-country implementation, Single application for the management of multiple farms around the globe

Can be integrated with existing devices and IoTs

Yearly or Monthly subscription plans available at low cost, low risk

Holitistic supply chain management

Can be integrated with existing devices and IoTs

IoT equipments

Requires high skilled field staff to implement and manage bots

Equipments are expensive and fragile

No log info

Sensors, robots, drones and cameras required to be placed on farms to monitor and operate.

Recurring maintenance costs for hardware

Computer imaging is done via sensor cameras and drones with manual operators

Each equipment has a defined set of operation, not one can show all stats

Not scalable, each farm data has to be managed separately

Difficult to integration with already implemented devices

Heavy initial investments

No supply chain management