Water, an essential resource for crop production, is becoming increasingly scarce, while cropland continues to expand due to the world’s population growth. Proper irrigation scheduling has been shown to help farmers improve crop yield and quality, resulting in more sustainable water consumption. Soil Moisture (SM), which indicates the amount of water in the soil, is one of the most important crop irrigation parameters. In terms of water usage optimization and crop yield, estimating future soil moisture (forecasting) is an essentially valuable task for crop irrigation. As a result, farmers can base crop irrigation decisions on this parameter. Sensors can be used to estimate this value in real time, which may assist farmers in deciding whether or not to irrigate. The soil moisture value provided by the sensors, on the other hand, is instantaneous and cannot be used to directly compute irrigation parameters such as the best timing or the required water quantity to irrigate. The soil moisture value can, in fact, vary greatly depending on factors such as humidity, weather, and time. Using machine learning methods, these parameters can be used to predict soil moisture levels in the near future. This paper proposes a new Long-Short Term Memory (LSTM)-based model to forecast soil moisture values in the future based on parameters collected from various sensors as a potential solution. To train and validate this model, a real-world dataset containing a set of parameters related to weather forecasting, soil moisture, and other related parameters was collected using smart sensors installed in a greenhouse in Chiang Mai province, Thailand. Preliminary results show that our LSTM-based model performs well in predicting soil moisture with a 0.72% RMSE error and a 0.52% cross-validation error (LSTM), and our Bi-LSTM model with a 0.76% RMSE error and a 0.57% cross-validation error. In the future, we aim to test and validate this model on other similar datasets.

Cultural heritage represents a reliable medium for history and knowledge transfer. Cultural heritage assets are often exhibited in museums and heritage sites all over the world. However, many assets are poorly labeled, which decreases their historical value. If an asset’s history is lost, its historical value is also lost. The classification and annotation of overlooked or incomplete cultural assets increase their historical value and allows the discovery of various types of historical links. In this paper, we tackle the challenge of automatically classifying and annotating cultural heritage assets using their visual features as well as the metadata available at hand. Traditional approaches mainly rely only on image data and machine-learning-based techniques to predict missing labels. Often, visual data are not the only information available at hand. In this paper, we present a novel multimodal classification approach for cultural heritage assets that relies on a multitask neural network where a convolutional neural network (CNN) is designed for visual feature learning and a regular neural network is used for textual feature learning. These networks are merged and trained using a shared loss. The combined networks rely on both image and textual features to achieve better asset classification. Initial tests related to painting assets showed that our approach performs better than traditional CNNs that only rely on images as input.