Fig 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
Deep learning, a subfield of artificial intelligence, has gained significant role in various domains, including agriculture. With the growing need to improve agricultural practices, enhance productivity, and face challenges such as crop yield prediction, disease detection, weed management, irrigation optimization, and livestock monitoring, deep lea...
Contexts in source publication
Context 1
... combining sensor data, satellite image, and historical records, deep learning models can provide valuable comprehensions into soil moisture levels, nutrient deficiencies, and irrigation needs. This provides farmers to apply water, fertilizers, and other inputs precisely, reducing waste and optimizing plant growth conditions (Fig 1 & 2). ...
Context 2
... learning, as a subset of artificial intelligence (AI), plays a vital role in enabling smart agriculture by analyzing large amounts of data and making accurate predictions (Espejo-Garcia et al. 2019). Here are some ways in which deep learning is applied in smart agriculture (Fig 6& 10 Fig 7). Here is how deep learning is applied in crop yield prediction (Koirala et al. 2019). ...
Context 3
... learning also playing a major role in livestock monitoring and management to providing valuable insights into animal behavior, health, and overall welfare (Atzberge 2013).Analyzing video feeds, sensor data, other forms of information, deep learning models can help farmers monitor livestock, detect anomalies, and make informed management decisions (Fig 12). From video feeds or sensor data can detect abnormal behavior, signs of distress, or health issues ( Bhagyalaxmi et al. 2016;Baweja et al. 2018). ...
