Digital t echnologies in agricult ure and rural areas stat us report
Challenges in AI adoption in agriculture
tải về 0.51 Mb. Chế độ xem pdf
|
48427-Article Text-152209-1-10-20200610
|
Challenges in AI adoption in agriculture Although AI presents immense opportunities in agriculture application, there still prevails a deficiency in familiarity with advanced high tech machine learning solutions in farms around the world. Exposing farming to external factors like weather conditions, soil conditions and vulnerability to the attack of pests is high. A crop raising plan scheduled at the start of the season might not seem to be good at the start of harvesting as it gets influenced by external parameters. AI systems too require a lot of data for training machines, to take precise forecasting or predictions. Just in case of a very large area of agricultural land, spatial data could be collected easily while getting temporal data is a challenge. The various crop specific data could be obtained only once in a year when the crops are grown. As the database takes time to mature, it involves a substantial amount of time to construct a robust AI machine learning model. This is a major reason for the utilization of AI in agronomic products like seeds, fertilizer and pesticides than that of on field precision solutions. In conclusion the future of farming in the times to come is largely reliant on adapting cognitive solutions. Though a vast research is still on and many applications are already available, the farming industry is still not having sufficient service, remains to be underserved. While it comes down in dealing with realistic challenges and demands faced by the farmers, using AI decision making systems and predictive solutions in solving them, farming with AI is only in a nascent stage. To exploit the tremendous scope of AI in agriculture, applications should be more robust. Then alone it will be in a position to handle frequent shifts and changes in external conditions. This would facilitate real time decision making and sequentially utilize appropriate model/program for gathering contextual data efficiently. The other crucial aspect is the extortionate cost of the various cognitive solutions for farming readily available in the market. The |