Open Access Open Access  Restricted Access Subscription or Fee Access

Predictive Farming Using Image Based Machine Learning

Seema Shingade, Omprakash Rajankar

Abstract


Agriculture sector is considered as central pillar of Indian economics contributing approximately
18% of total GDP employing almost 78% of rural population. Export of agro- based commodities has
increased by 7-folds in past 1.5 decade. Therefore, it is necessary to uplift quality of agro-commodities
productions. Improving crop quality and quantity by sowing appropriate crop according to soil type
and weather condition become an hour’s need today. There are variety of soil series available in India
and generally, cultivation of crops is specific to soil, climate, nutrients, and amount of water
requirement. Another most concerned factor is plant disease deciding crop’s quality and quantity; it
estimated that every year up to 40% of crop yield worth 5 million crores of rupees is lost due to such
disease condition, pests, or weeds. Identification of such plant diseases and categorizing them in
systematic way becomes essential today. Principal problem associated with identification and
categorization of plant diseases is incapable human intervention on vast agro-fields which resulted in
unnoticed onset of plant disease. Even a single infected plant is capable of spreading the disease to
other plants on field; therefore, prompt treatment is required in order to save quality of crop. The given
problems encouraged to develop machine learning system which not only helps to predict the newer
crops as per soil type may be in between two major crops to maintain the soil fertility but also
accurately detect the onset of disease spreading over plant. A model developed for classifying soil
series and providing suitable crop suggestion has been tested by applying different kinds of machine
learning algorithms, particularly image processing using CNN algorithm gained expertise acceptance
level thus encouraged to try this new technology. The output images shown in the results indicate that
with image processing, CNN algorithm can accurately provide a crop suggestion and early disease
identification.


Full Text:

PDF PDF

References


Statista. (Jan, 2021). Agriculture in India—statistics & facts: Available at https://www.statista.com/topics/4868/agricultural-sector-in-india/.

Clear IAS. (April, 2021). Soils of India: Classification and characteristics. Available at https://www.clearias.com/soils-of-india-classification-characteristics/.

N Goel, D Jain, A Sinha. Prediction model for automated leaf disease detection & analysis. 2018 IEEE 8th International Advance Computing Conference (IACC). Greater Noida, India. 2018, Dec 14–15.

TT Mim, MH Sheikh, RA Shampa, MS Reza, MS Islam. Leaves diseases detection of tomato using image processing. 2019 8th International Conference System Modeling and Advancement in Research Trends (SMART). Moradabad, India. 2019, Nov. 22–23.

P Sharma, P Hans, SC Gupta. Classification of plant leaf diseases using machine learning and image preprocessing techniques. 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence). Noida, India. 2020, Jan. 29–31.

K Ahmed, TR Shahidi, SM Irfanul Alam, S Momen. (2019). Rice leaf disease detection using machine learning techniques. (Online) Available at https://www.semanticscholar.org/paper/Rice-Leaf-Disease-Detection-Using-Machine-Learning-Ahmed-Shahidi/7525a7949887d6de87c94d26ad227bd844608757.

BS Kusumo, A Heryana, O Mahendra, HF Pardede. Machine learning-based for automatic detection of corn-plant diseases using image processing. 2018 International Conference on Computer Control, Informatics, and its Applications (IC3INA). Tangerang, Indonesia 2018, Nov 1–2.

M Kalimuthu, P Vaishnavi, M Kishore. Crop prediction using machine learning. 2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT). Tirunelveli, India. 2020, Aug. 20–22. Available at: https://www.semanticscholar.org/paper/Crop-Prediction-using-Machine-Learning-Kalimuthu-Vaishnavi/939166f5b7c7291282cb7b1f5e0f9dec1275516e.

SAZ Rahman, K Chandra Mitra, SM Mohidul Islam. Soil classification using machine learning methods and crop suggestion based on soil series. 21st International Conference of Computer and Information Technology (ICCIT). Dhaka, Bangladesh. 2018, Dec. 21–23. Available at: https://www.semanticscholar.org/paper/Soil-Classification-Using-Machine-Learning-Methods-Rahman-Mitra/c6154ecadd374a50345980e2d5be0cc46c51027f. 2021.


Refbacks

  • There are currently no refbacks.