LoRaWAN-based Network for Harvest Time Estimation in Cistus ladanifer

Smart agricultural solutions contemplate the use of Wireless Sensor Networks (WSNs) to optimize resource use and decision-making. This study proposes deploying a LoRabased WSN to monitor $\alpha$-pinene production in Cistus ladanifer shrubs, aiming to estimate the optimal harvest time for obtaining the maximum yield of its essential oil. The communication system integrates LoRa and IEEE 802.11 technologies within an IoT framework, utilizing a layered data transmission system comprising edge and fog layers. Data transmission was tested at distances ranging from 678 to 14,700 meters over 28 iterations. MQ gas sensors recorded $\alpha$-pinene data, achieving a validation dataset accuracy of $99.79 \%$ with Cubic SVM and Fine KNN, and a test dataset accuracy of 62.5% with Kernel Naive Bayes using 11 to 13 features. Results showed the implementation of LoRa technology in our system offers substantial benefits in terms of range, reliability, and power efficiency, thus supporting the overall functionality and scalability of the network. Identifying the peak concentration of $\alpha$-pinene will aid in harvesting Cistus ladanifer at the optimal time to maximize yield. Integration of decision support systems for optimized crop yields and exploring alternative machine learning techniques with higher accuracies could be explored in future studies.