Browse Prior Art Database

Method to recommend type of crop and the best time to plant

IP.com Disclosure Number: IPCOM000234019D
Publication Date: 2014-Jan-07
Document File: 2 page(s) / 54K

Publishing Venue

The IP.com Prior Art Database

Abstract

Method to recommend type of crop and best time to plant. Analytics has a great potential to assist the agricultural industry. One of the applications is in the field of crop yield and plantation advice. The core idea of this invention is to cross mine and gain insight from natural language agricultural articles, weather pattern data and current weather sensor (GIS data) etc. to predict the type of crop to plant and when to plant. The learning model for such a system uses key data points such as soil type, weather, shifts in weather and harvest time by space. This type of system would be advantageous for short duration harvest time crops, that the farmer has a choice of planting but can get the best yield per crop type from a software as a service system in rural areas to take advantage of the vast knowledge of agricultural data and historical weather pattern.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 51% of the total text.

Page 01 of 2

Method to recommend type of crop and the best time to plant

One of the applications is in the field of crop yield and plantation advice. Large amount of information exists on these topics in different forms. There are huge databases of literature on soil type, weather conditions and weather patterns. The data can be obtained from books or scientific nature, agricultural journal articles about crops and web forums. Additionally, there is a growing use of location specific sensors that act as a data point and give real time information about the weather conditions. Their sources of data include Geographical Information Systems (GIS) information on soil texture, web data about the region , its soil, weather patterns/ articles about yield in a specific region.

Companies such as ESRI are in the location analytics business. These companies provide high-quality data for GIS analytics. For example, one can get imagery data, base maps, and climate change data. Such private players provide analytics and data based on GIS information but they don't go far enough with combining a natural language processing system with this analytics data to provide key insights for agriculture.

Disclosed is a method to cross mine and gain insight from natural language agricultural articles, weather pattern data and current weather sensor (GIS data) to predict the type of crop to plant and when to plant based on the cross section of data and a learning model based on the key data points for soil type, weather, shifts in weather and harvest time by space.

This would be advantageous for short duration harvest time crops that the farmer has a choice of planting but can get the best yield per crop type from software as a service system in rural areas to take advantage of the vast knowledge of agricultural data and historical weather patterns.

The advantage for this system would be given a location and some simple information on crop types available, a user in a remote part of the world can ask which crop would be best to plant now for the best yield and IBM Watson* would be able to give them a reasonable answer, with confidence and evidence to support the case.

The training on agricultural literature content would note and look for features based on crop type, harvest time, rainfall amount, water requirements, soil type and historical weather patterns for a particular region. GIS information and historical weather information would be cross mined and input for that data or matched for typical characteristic requirements for a crop type on a particular similar soil type. Based on these factors a series of training models would be developed to per crop and soil type for the agricultural factors that affect growth. The system can then be given a location series of crop types...