Statistical verification of 16-day rainfall forecast for a farmers advisory service in Pakistan

Bhatti, Muhammad Tousif; Anwar, Arif A.

doi:10.1016/j.agrformet.2022.108888

Cited by 4 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Before a model is even proposed, it is important to look at how manual predictive models may be enhanced and then we can address how to formulate machine models. Typical methods used in traditional agricultural prediction include the monitoring of nutrient in the soil, a review of past rainfall patterns to forecast subsequent rainfall [7], an analysis of the types of seeds used and their historical yield [8] and examination and analysis of typical pests and diseases that may affect a certain geographical area [9]. What can be noted in what has been discussed above is a question as to why a certain event that would require measurement happens.…”

Section: IImentioning

confidence: 99%

Current Trends in Machine-Based Predictive Analysis in Agriculture for Better Crop Management - A Systematic Review

Chibuye

Phiri

2023

zictjournal

View full text Add to dashboard Cite

The use of Artificial Intelligence in agriculture is a novel approach that promises many benefits. Notable is the emphasis by nations of the world to end hunger by 2030 as enshrined in Sustainable Development Goal number 2[1]. To end world hunger, the fundamental ways of doing things in and around the agricultural space will have to change by adopting much more sustainable models and relooking at the supply chain system with the space. For example, it is noted that more food goes to waste through spoilage than is required to feed all the hungry on earth. While in other parts of the globe, the food supply would be sufficient were it not for the stock that spoils due to pests and diseases. It the goal of this paper to provide a possible solution for the second scenario on spoilage due to pests and diseases by adopting Artificial Intelligence approaches such as Machine Learning and tweaking existing methods by improving the overall prediction score. We provide areas of interest that may be considered and show that further research in the subject may yield positive results in the field of Predictive Analysis as concerns the field of agriculture. A Systematic Review is done on over 20 pieces of literature around the field of Predictive analysis and notable gaps are highlighted while areas of possible improvement are also indicated. It is then against this backdrop that the highlighted areas of improvement may later be tested in subsequent work.

show abstract

Section: IImentioning

confidence: 99%