WISRAN

Live Lean Forming

Header img

Introduction


WISRAN is a revolutionary startup idea, selected by MIT boot camp. It uses data sciences to measures time variations of farming activities to manage revenue leak in industrial agriculture processes. It collects large volume of real-time data from vehicles via sensors, relays it to, a state of the art, machine learning engine to compute critical analytics. It monitors agricultural processes in real-time as well as suggests fixes to optimize processes in terms of time and cost.

Noteable Challanges

Tick icon

Limited time and budget

Provided with all of its complexity, we had to prove our idea, by developing a minimum viable product, within a season i.e. 3 months as we didn’t have enough budget to record data of whole year farming cycle covering all processes and seasons.

Tick icon

Real-time activity mapping

As different industrial farming vehicles, each having different size, speed and movement actions were involved even in a single process, identification of current activity was dependent on number of variables like vehicle type, vehicles’ relative speed, distance of vehicles from each other, vehicle dimensions etc. We had to develop a rule engine that analyses a large set of variables and determines current activity and its relative stage.

Tick icon

Scalability

Scalability was a real challenge as adding a single node in the system adds huge volume of data. We had to design a totally decoupled architecture that keeps all software components, along data pipeline and data aggregation engine in their optimally efficient state and ensures that all analysis, aggregation and computation on huge set of data provides a real-time picture.

Tick icon

Complex Business Domain

Being oldest profession on earth, farming has largest knowledge base of processes and each one has numerous variants. Farmers use slight variations of a single process based on their experience, field size, farm size and budget etc.In 1st place, large volume of raw data was available to understand and experiment. With the help of this raw data, understanding all variants of processes and identifying inefficiencies in them, was itself a great challenge, because each farmer and its flavor of a process, could be inefficient at a different stage.

Solutions of Challanges

Tick icon

Limited time and budget

Our years long experience of managing medium and large complex projects helped us keeping this project on its planned trajectory. We followed Agile processes, divided relevant stories in sprints with complete focus on adding maximum business value in each sprint.

Tick icon

Real-time activity mapping

We used Apache Kafka and Nifi to receive and channelize data streams, being relayed towards our rule engine powered by Apache spark, that analyzed and made aggregations based on complex rules at great speed.

Tick icon

Scalability

The decoupled infrastructure design rescued us. We designed system in three layers, a data pipeline, core engine and data layer. Each of these layers are multi-node systems and we can add multiple nodes in each layer according to system demand, anytime.

Tick icon

Complex Business Domain

Our onsite manager visited original site and conducted dozens of interviews with client, business stake holders and vehicle operators.Various interactive meetings and brainstorming sessions were held. With well-organized collaborative effort we were able to convert business requirements to stories and epics.

Result

Wisran is live with an Android and an iOS app. WISRAN has now successfully automated 56713 acres of industrial agriculture fields and made its way to Australia by winning a grant from Australian government.

  • Customers/Companies On board: 9
  • Equipment Integrated: 150
  • Operators: 231
  • Fields Automated: 680
  • Acres Automated: 56713
  • Seasons Covered: 4
  • Processes Automated: 14

Technology Stack

Ruby On Rails

Java

Swift

Apache Kafka

Apache Nifi

Apache Spark

Client's feedback


I’ve really enjoyed working with guys at Clustox. We’ve brainstormed for hours on minute details of WISRAN. Without them, it would really be hard to launch in record time and capture my first season on the fly.

Not available

Arsalan Lodhi

Founder & CEO WISRAN

Let's start new project together

Connect TM

Header img

Bookafy

Header img