Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Agricultural Recommendation System based on Deep Learning: A Multivariate Weather Forecasting Approach

Md Zubair, Md. Shahidul Salim, Mehrab Mustafy Rahman, Mohammad Jahid Ibna Basher, Shahin Imran, Iqbal H. Sarker

TL;DR

This work tackles the challenge of climate variability affecting agriculture by building a multivariate weather forecasting system for Bangladesh. It employs a stacked Bi-LSTM (three Bi-LSTM layers plus a TimeDistributed layer) trained on data from 35 weather stations to forecast Rainfall, Temperature, Humidity, and Sunshine, and to issue extreme-weather alerts. Forecast outputs feed into a knowledge-based agricultural recommendation module that accounts for Bangladesh’s cropping seasons and flood/drought-prone zones, including a nearest-station lookup via the Haversine formula. The approach achieves high predictive accuracy (average $R^2$ around 0.9824–0.9838) and offers practical decision support for farmers, with potential to generalize to other countries given region-specific training data.

Abstract

Agriculture plays a fundamental role in driving economic growth and ensuring food security for populations around the world. Although labor-intensive agriculture has led to steady increases in food grain production in many developing countries, it is frequently challenged by adverse weather conditions, including heavy rainfall, low temperatures, and drought. These factors substantially hinder food production, posing significant risks to global food security. In order to have a profitable, sustainable, and farmer-friendly agricultural practice, this paper proposes a context-based crop recommendation system powered by a weather forecast model. For implementation purposes, we have considered the whole territory of Bangladesh. With extensive evaluation, the multivariate Stacked Bi-LSTM (three Bi-LSTM layers with a time Distributed layer) Network is employed as the weather forecasting model. The proposed weather model can forecast Rainfall, Temperature, Humidity, and Sunshine for any given location in Bangladesh with an average R-Squared value of 0.9824, and the model outperforms other state-of-the-art LSTM models. These predictions guide our system in generating viable farming decisions. Additionally, our full-fledged system is capable of alerting the farmers about extreme weather conditions so that preventive measures can be undertaken to protect the crops. Finally, the system is also adept at making knowledge-based crop suggestions for flood and drought-prone regions.

Agricultural Recommendation System based on Deep Learning: A Multivariate Weather Forecasting Approach

TL;DR

This work tackles the challenge of climate variability affecting agriculture by building a multivariate weather forecasting system for Bangladesh. It employs a stacked Bi-LSTM (three Bi-LSTM layers plus a TimeDistributed layer) trained on data from 35 weather stations to forecast Rainfall, Temperature, Humidity, and Sunshine, and to issue extreme-weather alerts. Forecast outputs feed into a knowledge-based agricultural recommendation module that accounts for Bangladesh’s cropping seasons and flood/drought-prone zones, including a nearest-station lookup via the Haversine formula. The approach achieves high predictive accuracy (average around 0.9824–0.9838) and offers practical decision support for farmers, with potential to generalize to other countries given region-specific training data.

Abstract

Agriculture plays a fundamental role in driving economic growth and ensuring food security for populations around the world. Although labor-intensive agriculture has led to steady increases in food grain production in many developing countries, it is frequently challenged by adverse weather conditions, including heavy rainfall, low temperatures, and drought. These factors substantially hinder food production, posing significant risks to global food security. In order to have a profitable, sustainable, and farmer-friendly agricultural practice, this paper proposes a context-based crop recommendation system powered by a weather forecast model. For implementation purposes, we have considered the whole territory of Bangladesh. With extensive evaluation, the multivariate Stacked Bi-LSTM (three Bi-LSTM layers with a time Distributed layer) Network is employed as the weather forecasting model. The proposed weather model can forecast Rainfall, Temperature, Humidity, and Sunshine for any given location in Bangladesh with an average R-Squared value of 0.9824, and the model outperforms other state-of-the-art LSTM models. These predictions guide our system in generating viable farming decisions. Additionally, our full-fledged system is capable of alerting the farmers about extreme weather conditions so that preventive measures can be undertaken to protect the crops. Finally, the system is also adept at making knowledge-based crop suggestions for flood and drought-prone regions.
Paper Structure (37 sections, 8 equations, 16 figures, 11 tables)

This paper contains 37 sections, 8 equations, 16 figures, 11 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Data Collection and Prepossessing
  4. Dataset collection
  5. Insight about Dataset
  6. Distribution of the Data
  7. Stationary check using Augmented Dickey-Fuller test
  8. Data preprocessing
  9. Data conversion in the desired format
  10. Wind speed and wind direction in vector
  11. Missing value handling
  12. Merge the files
  13. Normalize the data
  14. Train and test set generation
  15. Proposed Methodology
  16. ...and 22 more sections

Figures (16)

  • Figure 1: Districts of Bangladesh having weather stations.
  • Figure 2: Last 10 years monthly weather trend of average (a)Rainfall, (b)Temperature (c)Humidity and (d)Sunshine of Dhaka City
  • Figure 3: Probability distribution of daily weather records (a) Rainfall, (b)Temperature, (c)Humidity, and (d)Sunshine for 7 major districts of Bangladesh.
  • Figure 4: Stacked bar plot for yearly rainfall for the last 20 years of Dhaka city and months are noted with different colors on the right-side legends.
  • Figure 5: Distribution of monthly temperature of Dhaka city with box plot.
  • ...and 11 more figures