With the use of precision agriculture (PA), the cultivation of inputs can be managed in an environmentally sustainable manner. PA can target rates of chemicals, seed, and chemicals for soil and other variables by applying site-specific knowledge. PA replaces physical inputs with information and knowledge. A study of the literature shows that PA can support production agriculture's long-term sustainability in a variety of ways, supporting the common-sense notion that PA should lessen its ecological impact by using chemicals like pesticides and fertilizers just when and where they are necessary. Environmental advantages of precision agriculture result from more focused input utilization that lowers losses from extra applications as well as from reductions in losses owing to nutrient problems, weed escapes and insect damage, etc. A decrease in the emergence of resistant species to pesticides is among the additional advantages. An essential technique to produce crops in a sustainable and environmentally friendly manner is through precision agriculture, which is a growingly recognized type of crop production. Precision-based agricultural has been made possible by subsequent technological developments and advances like computational sciences (decision support systems) and information technology. To address today's difficulties, emerging completely understanding algorithms must be redesigned. So, utilizing a deep learning algorithm, this research proposes a big data statistics agriculture surveillance system (BDA-AMS) to ensure extremely accurate grain output forecast in precise farming and managing the economy.