Session 41 - Agroforestry, Forest and Agricultural Sustainability

Valonia oak is the most widespread tree species found in the Aegean island of Kea - Cyclades. It forms traditional agroforestry systems since intensive agriculture is not easily practiced in the island due to the xerothermic climate and the rough terrain with steep slopes. This system has traditionally supported the local economy by its multiple products while respecting the environment. In almost all the cases, it is found in traditional terraces which were constructed since ancient times by local farmers. Even if these systems have been threatened by abandonment and change of land use (mainly for touristic purposes), there has been an increasing interest lately motivated by the higher price gained by valonia oak acorns trade and demand for agrotouristic activities. An experimental plot was established under the framework of the AGFORWARD (FP7) research project, where two commercial pasture mixes were tested for their productive capacity under shade. Soil properties were evaluated at the end of the experiment to evaluate the effect of intercropping on the economy of certain nutrients. The importance of the environmental and economic function of this system is highlighted and suggestions are made for its preservation.

The organic carbon percentage is concomitant indicating the mineralization of nutrients and the ability of the soil to hold nutrients cations, structural stability, and water holding capacity. It is necessary to know the quantity of carbon for healthy soil and avoid the production related problems which can affect the sustainable agriculture model. In existing approaches, to quantitively calculate soil carbon, sample collection and in-situ laboratory testing are performed. In this work, a novel framework is proposed which is based on Partial Least Square Regression and Long Short-Term Memory networks to quantify soil organic carbon from the LUCAS dataset. Samples of LUCAS dataset are used as input to this framework. The samples are pre-processed by PLS to reduce their dimensions. These pre-processed samples are then passed to the LSTM, a Deep learning framework to build an efficient prediction model. The proposed framework performed more accurately, and its effectiveness is shown by comparing it with existing regression models.

Inhomogeneities of soil properties are responsible for within-field variations on the growth and final yield of crops. In this paper the variations of a Normalized Difference Vegetation Index (NDVI) field map, obtained through a camera mounted on an Unmanned Aerial Vehicle, were correlated with soil and plant properties measured in a typical maize cultivated field. Subsequently, the perspective of organizing the field into differential management zones through the NDVI was evaluated. The coefficient of variation for sand, silt, clay and soil organic matter content at five points was found to exceed 11% while the corresponding value for biomass and yield were greater than 14%, indicating significant spatial field soil heterogeneity and variations on plant growth. When correlated to NDVI, sand content exhibited a negative correlation (r=-0.86), while in the case of silt, clay, organic matter content, biomass and yield the correlation was positive (r>0.8). Lastly, the NDVI confirmed to be a powerful tool for the delineation of deferential management zones.