Predication of soil pH using HSI colour image processing and regression over Guwahati, Assam, India

Abstract

Soil is known to be the most valuable natural source for all agriculture fields. Soil has two properties, namely- physical and chemical. These properties include soil moisture, texture, etc. and the latter include pH value. Soil texture plays an important role in crop cultivation. The physical properties of soil such as texture and granular size determine the water and nutrient holding capacity. Also the chemical property like pH value is very important for plant growth and development. Soil having pH value between 5.5 and 7 is optimal for agricultural purpose. Hence, a detailed study of soil pH property is necessary for cultivation. But laboratory method of soil pH calculation is a very costly and tedious process. Therefore, it is essential to develop an expert-based system that will overcome this issue. However, the system must be able to give correct result and should match with those conducted in laboratory. Farmers analyze pH either in lab or by soil pH card based on soil image color. But this is not an effective method since it relies heavily on human perception. Hence, we have developed an expert based system which can determine the pH of the soil without any human error. For this, we have conducted our experiments with the help of MatLab tool and smart phone as we have concerned about the rural farmers. We have analyzed and compared the proposed system results with the traditional laboratory methods with regression and have found 86 % accuracy in our model.