IoT-Based Precision Agriculture

Bangladesh agriculture sector is plighted by the following problems:

• Inadequate irrigation management
• Excessive use of resources including fertilizers and pesticides
• High production cost for farmers, and
• Largest GHG emitting sector.

We are proposing to design, test and deploy Internet of Things (IoT) based Precision Agriculture System (Prototype). It will employ data from multiple sources including sensors to improve crop yields and cost-effectiveness of crop management strategies.

The project will help all major stakeholders in the following manners:

• can monitor soil and plant parameters, automate field management, minimize pesticide, fertilizer and irrigation needs. The farmers can determine peak conditions for plant growth and what nutrients their crops need.
• will get safer product with acceptable level fertilizer and pesticide residues at a competitive price.
• will be able to ensure sustainable agriculture sector in line with SDG Goals.

Climate change will bring greater fluctuation in crop production, food supplies, and market prices and will aggravate the situation of food insecurity and poverty in Bangladesh, which will adversely affect the livelihoods of millions of people of this country. Besides, agriculture is the largest user of water, can reach up to 90% of total water consumption, and also the largest GHG emission contributor. It is estimated that climate change will reduce 8-17% rain fall by 2050, which will have an impact of yield decrease by 8-10%. Thus, Bangladesh agriculture sector needs to move toward IoT-based precision agriculture, which is a proven technology, to meet the future challenge.

The agricultural sector contributes nearly 15% of the country's GDP and provides employment about 41% of the labor forces. Availability of agricultural land in Bangladesh is gradually declining. The shifting rate of agricultural land to non-agricultural use is about 1% per year.

Our proposed solution aims i) to reduce water use by 30%, ii) to reduce fertilizer and pesticide use by 20%, iii) to increase productivity by 20% iv) to reduce production cost by 20% v) to optimise machine learning decision support tool and vi) to develop a comprehensive crop management database.

The Project Objectives are as follows: 1) Design and develop a functional IoT enabled scalable agriculture system prototype 2) Use Brinjal as use case to test the system 3) Conduct feasibility analysis and business model development 4) Develop deployment strategy of the prototype system

The project will have the following deliverables: 1) Customized IoT database for brinjal 2) Customized IoT analytics software 3) Mobile and desktop application for end user- Decision Support System (DSS) 4) Functional IoT enabled Agriculture Prototype ecosystem 5) Scalable ecosystem deployment strategy and economic analysis

The major technology and components includes: 1) IoT Sensors (e.g., Soil temperature and moisture sensor, Leaf Wetness sensor, Solar radiation sensor 2) Analytics Software (Available Open Source IoT Agriculture Analytics Software) 3) Network Connectivity (available wireless communication technology) 4) Database (Mongodb) 5) Mobile Application (Android application)

Agriculture plays a vital role in growth and sustainability of the economy of Bangladesh, however vulnerability of this sector due to climate change, excess resource use and associated pollution, resource depletion, and food insecurity have not been assessed adequately to ensure the sustainability of Bangladesh agriculture.

About 60% of farmers are functionally landless and depend on sharecropping of land owned by the others. These farmers are directly impacted due to increased production cost of their crops and face significant challenges due to high cost of resources.

The solution proposed is geared towards the agriculture sector. In particular, the project will work with the farmers and researchers of this sector. The project team has undertaken a feasibility study (proof of concept) and have discussed the idea and solutions with farmer. The farmers will be the most important stakeholder in implementing the project since they will be users of the prototype solution.

The fertility status of soils is extremely variable and it is estimated that more than 100 kg nutrients/ha/year are mining out from the soil system. Besides, excess pesticides and irrigation are often used in crop production. Our solution will assist farmers to determine resource needs for their crop production.

The project will design, develop, deploy a scalable functional IoT enabled scalable precision agriculture system that will help mitigate the effects of climate change in Bangladeshi agriculture sector as identified so far. The project will optimize crop management strategies by controling fertilizer inputs, irrigation management, and pesticide application resulting into safe produce.

In summary, the project will help support small-scale farmers to  access new technology, knowledge and a sustainable business model to improve yields while sustaining productivity.

Bangladeshi agriculture sector the backbone of the country’s economy is threatened by climate change resulting in a) access water use up to 90% of total water consumption b) largest GHG emission contributor c)  reduction of agriculture land by 1% a year c)  vulnerable fertility status of soils, e.g.,100 kg nutrients/ha/year are mining out from the soil system. d) sharp increase in fertilizer use and irrigation as consequence. In the circumstances, innovative solutions are required and with that goal the project will design, develop, deploy a scalable functional IoT enabled scalable precision agriculture system. Precision agriculture technology has yielded good results in other countries faced with similar problems. There are enterprises like “iFarmer” and “Ajkerkrishi” working in the agriculture sector in Bangladesh, but the use of precision agriculture technology and a functional business model for farmers is novel in the context of the country.  The project will ensure innovative cost effective access to a service package to farmers that are essentially based on the following four stages, a) Sense: Monitoring of critical plant parameters 24x7x365 from the farm and uploading the data to our cloud platform; b) Analyze: This data will then be analyzed and make accessible to the farmer anytime, anywhere on any device for data-driven decision making; c) Predict: Our prediction algorithm will continuously analyze the farm level data to predict the ideal growth conditions, resource requirements including irrigation, sprays and other preventive measures; and d) Act: Finally, the Farmer gets notified on his device and acts accordingly.

Precision Agriculture (PA) system to be used will have essentially two components a) sensors and b) artificial intelligence powered machine learning algorithm.  The system will include IoT enabled sensor measuring soil temperature and moisture, leaf wetness, solar radiation etc., that will be integrated in the farm. The sensor data will be "wirelessly" transmitted and a decision support tool comparing the information with cloud database will give predictive solutions/suggestion regarding water, fertilizer, pesticide, seeding and notify farmers regarding risks of plant diseases and recommend appropriate actions. The service will be delivered through a user-friendly android application that the farmers can use through the mobile phones.  Many sensors are currently available and used for data gathering or information provision as part of the PA implementation. These devices are designed for both in-situ and on-the-go recording. Devices exist to assess the status of soils, such as apparent electrical conductivity (ECa) sensors, gamma-radiometric soil sensors, and soil moisture devices, among others. Powerful analytical software, predictive algorithms, machine learning and the ability to interpret and use data which are the basic component of the loosely coined term IoT, compliments in realizing precision agriculture.

The implementation of PA has become possible thanks to the development of sensor technologies combined with procedures to link mapped variables to appropriate farming management actions such as cultivation, seeding, fertilization, herbicide application, and harvesting (https://bit.ly/2N468X5). Variable Rate Technology (VRT) that allows precise seeding, optimization on planting density and improved application rate efficiency of herbicides, pesticides and nutrients, resulting in cost reduction and reducing environmental impact. Powerful analytical software, predictive algorithms, machine learning and the ability to interpret and use data which are the basic component of the loosely coined term IoT, compliments in realizing precision agriculture (https://bit.ly/2YMClHB ;https://bit.ly/2YazRnu). IoT devices share the sensor data they collect by connecting to an IoT gateway or other edge devices where data is either sent to the cloud to be analyzed or analyzed locally. The analysis part is conducted using software based on high-precision algorithms. The mechanism that drives it is Machine Learning. The scientific field that gives machines the ability to learn without being strictly programmed (https://bit.ly/2N4OPVB). It has emerged together with big data technologies and high-performance computing to create new opportunities to unravel, quantify, and understand data intensive processes in agricultural operational environments. These technologies have successfully been applied in agriculture sector in different continents.

Bangladesh agriculture sector is vulnerable due to climate change, excess resource use and associated pollution, and high production cost. Climate change will bring greater fluctuation in crop production, food supplies, and market prices will aggravate the situation of food insecurity and poverty in Bangladesh. Precision agriculture based on IoT can potentially solve these problems. Precision agriculture improves crop yields and increase the cost-effectiveness of crop management strategies including fertilizer inputs, irrigation management, and pesticide application resulting into safe produce. The project will design and develop a functional IoT enabled scalable prototype precision agriculture system. The project will utilize machine learning decision support tool to deliver a comprehensive crop management system with the following specific outcomes based on existing performance indicator of the technology in other countries (https://bit.ly/30Tsjr8)- i) 10% decrease in water usage, ii) 15% reduction in fertilizer and pesticide, iii) 10% increase in overall productivity, iv) 10% decrease in seeding requirement, v) 10% increase in yield, vi) 10% decrease in production cost (excluding overhead cost), vii) 90% of time the system would be able to provide predictive solutions.

The project has developed the “proof of concept”. It has used the cultivation of  ”brinjal” as an illustrative case. At present the project has impacted 2 farmers and 10 staffs in various roles involved. Successful rollout of the prototype system in 20 small farms after 1 year is expected to impact more than  20,000 lives. The assumptions used in the calculations are as follows- each small firm has around 10 people involved including family members; each farm is expected to service around 1000 end consumers a year; and project team is expected to involve 100 employees in various capacity. After 5 years, if large scale deployment is successful (the system deployed in 2000 small farms) the number of lives impacted is expected to be 2 million (approximately). The same assumption as used previously is adopted for the calculation.   

The project has tested the proof of concept in phase 1. In phase 2 (after 1 year) the project aims to complete a wider test of the prototype system. Within the next 5 years (phase 3), the project team expects to complete commercial deployment of such technology in Bangladesh.

In 1 years time (phase 1) IoT precision agriculture system is expected to be employed to cultivate vegetables and oil seeds across a large area. The cultivation area can be over 1 acres. Successful completion of phase 2 will enable large scale deployment of precision agriculture in Bangladesh with the help of various government and non-government development agencies. In this phase (within 5 years), it is assumed that extensive science and knowledge, business model and infrastructure will be present which is necessary for large scale deployment of the technology for a variety of crops, vegetables and fruits. The entirety of the technology including installation of hardware and access to software services can be provided at a subsidized cost to the farmers. The cost savings and subsidy would mean that the use of such technology as economically viable option for the farmers to deliver safer produces at a cheaper price.

There are three main types of barriers/risks that can affect the project namely 1) Technical Risks 2) Financial Risks 3) Market Competition

Barrier  (0-5 year)

Financial Risk- Unavailability of fund or problems with cash-flow. The firm undertaking the project has already invested in conducting background research and to test the proof of concept. However, it should be acknowledged that financial support is needed to pursue extensively test and rolling-out of the prototype system. 

Barrier  (1-5 year)

Technical risks- The risk related incapability of the project to successfully integrate technology and deliver the promised results.

Market Competition- Scope of similar technology to be deployed in Bangladesh by competitors. The project team is not aware of any similar project being implemented in Bangladesh.

Mitigating Financial Risk/barrier: In this regard we are willing to partner with donor and government agencies and other private investors.

Mitigating Technical Risk/barrier: The firm undertaking the project specializes in technology development and management. In addition, the science behind precision agriculture and other technology development is proven in other countries. Furthermore, the project team will include various domain experts such as agriculturists to counter such risks.

Mitigating Market Risk/barrier: The knowledge, know-how, technology,

services and skills to be generated as deliverables of the project is
open source and for the betterment of the society and the country.

Dr. Saad Hasan is a specialist in technology integration and assessment. Experienced in project management and coordination experience in the UK and Bangladesh.

Dr. Mohammad Rashedul Hoque is experienced in applying industrial ecology tools and integrated environmental evaluation of new technologies.

Mr. Shovan Samaddar  has led and worked in mobile applications, IoT, machine learning and digital transformation projects for the enterprises based in Europe and USA.

Mr. Shafkat Reza Chowdhury is an expert in Agro-based product market research. He has a Master’s degree in International Business from Brunel University, UK.

Consultants-6 domain experts (agriculturist, data scientists, software experts, algorithm developers).

The project will be undertaken by Nodes Digital, a technology research management, integration, & development firm based in Dhaka, Bangladesh. The project team brings together the necessary skills and experience to run and complete the project successfully and on time.

Dr. Saad Hasan holds a PhD degree in Supply Chain Management. Dr. Hasan has collaborated with University of Bordeaux; (France); BIBA (Germany), Institute of Manufacturing (Cambridge University, UK) and large electronic manufacturers such as Magneti Marelly Group (France) and Siegert Electronic GmbH (Germany). Dr. Hasan will act as the Project Manager to deliver project outcomes.

Mr. Shovan Samaddar has over 10 years of experience in the IT and associated industries. He has led and worked across diverse business domains including crowdfunding, e-commerce, desktop & mobile applications, and digital transformation projects for the enterprises based in Japan, Europe and the USA. Mr. Samaddar will act as the Technical Manager in the project.

Dr. Mohammad Rashedul Hoque holds a PhD degree in Industrial Ecology from Universitat Autonoma de Barcelona (UAB), Spain. He has 10+ years teaching, research, and delivery experience related to environment management, operations and supply chain in Spain, Sweden, European Union and Bangladesh. Dr. Hoque will act as the Commercial Manager, supported by Mr. Shafkat Reza Chowdhury who has corporate experiences in various industries in Bangladesh and his areas of expertise are in the fields of Marketing, Sales, Service Marketing and International Business.

We have also on-boarded Agriculturist and other Domain Experts to deliver expected results of the project.

The proposed project aims to test the IoT enabled precision agriculture (PA) techniques in Bangladesh in small-scale (phase1). Successful completion and results of the project can be used in large-scale (Phase2) leading commercial deployment of such technology in Bangladesh (Phase3).

In phase2, the IoT enabled PA techniques can be employed to cultivate vegetables, oil seeds, tea and rice across a large area (1000ha) across Bangladesh in different locations. It is estimated that applying PA technology over 1000ha of land, the investment in technology across 3 years is $30/ha and the benefit from reduced overlap in spraying, fertilizer management, less soil compaction, fuel savings could be $21/ha annually.

In phase3, the large-scale deployment of PA in Bangladesh with the help of various government and non-government development agencies will help to achieve SDG goals as mentioned earlier. If PA is adopted in 1% of total cropped area in Bangladesh then a net economic benefit of at least $37million could be achieved annually with a return on investment (ROI) of 104%, which is excellent in any yardstick.

The major beneficiaries of the project are the farmers and various government agencies:

• Mobile and desktop application for end user- Decision Support System (DSS)
• Functional IoT enabled Agriculture Prototype ecosystem
• Scalable ecosystem deployment strategy and economic analysis.

The entire service/ product package can developed for commercial exploitation at the mature stage. This solution will be attractive for the farmers since it will enable 10-30% reduction of resource use for their produces.

Without Solve funding, the project team will not be able to pursue the opportunity to the same level of ambition, scale, or schedule. Thus, the development will proceed on a smaller scale, fragmented projects with limited access to equipment and resources, and will significantly increase risk and time to market.

With current COVID19 situation we may face difficulties in product/service distribution. Besides, New technology/ process adoption in the market is particularly challenging when the target customers are not well aware of the use of information technology in their agricultural/farming activities.

Mentorship and developing partnership for further funding strategies and improved revenue model is highly desired for achieve future financial sustainability of Nodes Digital Ltd. in the Bangladesh agriculture sector.

Most importantly, Solve funding will definitely add value to Nodes Digital's image within the targeted stakeholder community.