Time series forecasting is an important research topic among agriculture economics. Especially, multivariate, multi-step and multiple output prediction tasks pose a challenge in research as their nature requires the investigation of intra- and inter-series correlation. The common statistical methods like ARIMA and SARIMA fall short in this kind of tasks. Deep learning architectures like Convolutional Neural Networks and Long Short-Term Memory networks are quite good at modelling the structures of complex data relations. In this study, a new dataset is composed through manual collection of data from the Ministry of Commerce of Turkish Republic. The dataset contains daily trade volumes and prices of potato, onion and garlic, which are most commonly consumed products in Turkish cuisine. The data pertains to the period between January 1, 2018 and November 26, 2022 (1791 days). A simple CNN and LSTM architectures as well Random Forest machine learning method are used to predict the next 10-day prices of the products. Accordingly, three models provided acceptable results in the prediction tasks, while CNN yielded by far the best result (MAE: 0.047, RMSE: 0.070).

This paper investigates the causal relationship among GDP, agricultural, industrial and services sectors in Turkey for the period of 1968-2015. For this purpose, we employed Engle-Granger causality/block exogeneity Wald test, Impulse Response and Variance Decomposition analysis. The results showed unidirectional granger causality from agriculture to GDP and the other three sectors, while the agricultural sector is not influenced by the others. This is an expected result for any developing country where the agriculture accounts for a large proportion of national GDP, but an unexpected result for developed countries like European Union members to which Turkey has long been wishing to join. To our knowledge, although this method has been applied in various areas, sectoral causality has not been studied for Turkey before

Detecting plant disease is a complicated yet important task to enable sustainable production in agriculture. Especially, early and on-field disease detection provides an opportunity to producers to take necessary precautions before it causes dramatic losses. Corn is one of the most important agricultural products for many countries around the world. It constitutes the main nutrient intake for large populations. This study examines and analyzes the applicability of the pretrained models in corn disease detection. A number of well-known pretrained models including Xception, ResNet50, VGG16, EfficientNetB0, MobileNet and InceptionV3 have been employed for this purpose. SMOTE is employed to solve the imbalanced data and resulting bias problem, which is a common problem in plant disease dataset. The study results indicate that SMOTE provides a good solution to the imbalanced data problem and MobileNet, VGG16 and Xception can be used as base models to develop AI applications to detect corn diseases.

Climate has a significant impact on agricultural production. According to scientific data, climate change is having a growing impact on the planet's life, and different regions of the world are experiencing this impact in different ways. The greatest challenge to achieving sustainable development is climate change, which also poses a serious risk to the survival of humanity. It will have far-reaching consequences within the context of animal production, and particularly in regions of vital importance to the world's nutrition and livelihoods. All species have ideal climatic parameters for survival in animal husbandry, and changes to these variables have a negative impact on the quality and quantity of farm animals and animal products. There are four key areas where the effects of climate change on animal productivity can be studied. These include effects on pasture quality, effects on animal diseases and pests, effects on animal health, growth, and reproduction. They also include implications on the availability, quality, and price of feed crops. Planning for the sector's future is crucial in order to meet the population's food needs, lessen the impact of climate change on livestock output, and reduce the sector's contribution to global warming. Adapting animal husbandry to climate change is required to reduce all these harmful effects.

Agricultural Input Price Index is calculated and published by Turkish Statistical Institute each month in order to track the changes in prices of products and services that are used for current agricultural production and future investments. The prediction of the index will enable agricultural producers to make timely decisions regarding investment decisions and product preferences and will increase their competitiveness in the domestic and international markets. In order to predict changes in this index, (ARIMA, SARIMA) and deep learning models (CNN, LSTM) were used in a comparative way in the study. It is known that CNN and LSTM models capture both linear and nonlinear data traits. The prediction results are evaluated by Root Mean Squared Error (RMSE) and Mean Squared Error (MSE) metrics. According to the study results, ARIMA (RMSE: 0.16409, MSE: 0.0269247) and CNN (RMSE: 0.16994, MSE: 0.288791) models achieved the best results, and they are followed by LSTM model.