Phoenix palms cover more than 1.3 million hectares in the Mediterranean, Middle East, and North Africa regions and they represent highly valued assets for economic, environmental, and cultural purposes. Despite their importance, information on the number of palm trees and the palm distribution across different scenes is difficult to obtain and, therefore, limited. In this work, we present the first region-wide spatial inventory of Phoenix dactylifera (date palm) and Phoenix canariensis (canary palm) trees, based on remote imagery from the Alicante province in Spain. A deep learning architecture that was based on convolutional neural networks (CNN) was implemented to generate a detection model able to locate and classify individual palms trees from aerial high-resolution RGB images. When considering that creating large labeled image datasets is a constraint in object detection applied to remote sensing data, as a strategy for pre-training detection models on a similar task, imagery and palm maps from the autonomous community of the Canary Islands were used. Subsequently, these models were transferred for re-training with imagery from Alicante. The best performing model was capable of mapping Phoenix palms in different scenes, with a changeable appearance, and with varied ages, achieving a mean average precision ($mAP$) value of 0.861. In total, 511,095 Phoenix palms with a probability score above 0.5 were detected over an area of 5816 km². The detection model, which was obtained from an out-of-the-box object detector, RetinaNet, provides a fast and straightforward method to map isolated and densely distributed date and canary palms—and other Phoenix palms. The inventory of palm trees established here provides quantitative information on Phoenix palms distribution, which could be used as a baseline for long-term monitoring of palms’ conditions. In addition to boosting palm tree inventory across multiple landscapes at a large scale, the detection model demonstrates how image processing techniques that are based on deep learning leverage image understanding from remote sensing data.

Red palm weevil (RPW) is widely considered a key pest of palms, creating extensive damages to the date palm trunk that inevitably leads to palm death if no pest eradication is done. This study evaluates the potential of a remote sensing approach for the timely and reliable detection of RPW infestation on the palm canopy. For two consecutive years, an experimental field with infested and control palms was regularly monitored by an Unmanned Aerial Vehicle (UAV) carrying RGB, multispectral, and thermal sensors. Simultaneously, detailed visual observations of the RPW effects on the palms were made to assess the evolution of infestation from the initial stage until palm death. A UAV-based image processing chain for nondestructive RPW detection was built based on segmentation and vegetation index analysis techniques. These algorithms reveal the potential of thermal data to detect RPW infestation. Maximum temperature values and standard deviations within the palm crown revealed a significant (α = 0.05) difference between infested and non-infested palms at a severe infestation stage but before any visual canopy symptoms were noticed. Furthermore, this proof-of-concept study showed that the temporal monitoring of spectral vegetation index values could contribute to the detection of infested palms before canopy symptoms are visible. The seasonal significant (α = 0.05) increase of greenness index values, as observed in non-infested trees, could not be observed in infested palms. These findings are of added value for steering management practices and future related studies, but further validation of the results is needed. The workflow and resulting maps are accessible through the Mapeo^® visualization platform.

This paper presents a novel approach to identify and geolocate nutrient deficiencies in oil-palm plantations using a mobile application. The process starts when the user captures an image of an oil-palm leaf with the integrated camera of an Android smart device. Then, the application processes and classifies the image into four categories corresponding to: a healthy palm, or a specimen with a deficit of Potassium (K), Magnesium (Mg), or Nitrogen (N). Finally, the application shows the corresponding predictions on the screen and it includes the current timestamp and GPS coordinate. However, if the smart device has an internet connection, the application also sends the processed data to Microsoft Azure for long-term storage and it enables the visualization of historic predictions through a web report built with Microsoft Power BI. The developed application allows producers to obtain in situ diagnosis of plant deficiencies in their crops, helping nutrient management plans and crop management policies. The proposed solution can be easily scaled to hundreds of devices for field deployments because each mobile application is configured as an Internet-of-Things device in the Azure Cloud.