The main goal of the agricultural sector in Bangladesh is to maintain food security for a population of 160 million. Due to the increase in population and the decrease of agricultural land, this sector is under pressure to ensure food for its vast population. Bangladesh is predominantly an agricultural based country, and agriculture contributes remarkably to the national economy, employment rates, and consumption. Reliable and up-to-date information on crop yield predictions before the harvest is vital for the Government and its stakeholders to maintain food security, reservation, and trade. The goal of this paper is to investigate the strength of satellite data products as predictors for wheat yield prediction and to develop a prediction model using an Artificial Neural Network (ANN) simulation tool. Vegetation health indices Vegetation Condition Index (VCI), and Temperature Condition Index (TCI) developed by National Oceanic and Atmospheric Administration (NOAA) computed from Advanced Very High-Resolution Radiometer (AVHRR) sensor are tested for wheat yield prediction. Wheat is the second most vital food grain after rice in Bangladesh and plays a significant role in meeting the country’s food requirements. The predicted values from this model are compared with the actual yield. The result obtained from this model shows higher prediction accuracies.
The main goal of the agricultural sector in Bangladesh is to maintain food security for a population of 160 million. Due to the increase in population and the decrease of agricultural land, this sector is under pressure to ensure food for its vast population. Bangladesh is predominantly an agricultural based country, and agriculture contributes remarkably to the national economy, employment rates, and consumption. Reliable and up-to-date information on crop yield predictions before the harvest is vital for the Government and its stakeholders to maintain food security, reservation, and trade. The goal of this paper is to investigate the strength of satellite data products as predictors for wheat yield prediction and to develop a prediction model using an Artificial Neural Network (ANN) simulation tool. Vegetation health indices Vegetation Condition Index (VCI), and Temperature Condition Index (TCI) developed by National Oceanic and Atmospheric Administration (NOAA) computed from Advanced Very High-Resolution Radiometer (AVHRR) sensor are tested for wheat yield prediction. Wheat is the second most vital food grain after rice in Bangladesh and plays a significant role in meeting the country’s food requirements. The predicted values from this model are compared with the actual yield. The result obtained from this model shows higher prediction accuracies.