Using a Self-Organizing Map to Explore Local Weather Features for Smart Urban Agriculture in Northern Taiwan

Abstract

Weather plays a critical role in outdoor agricultural production; therefore, climate information can help farmers to arrange planting and production schedules, especially for urban agriculture (UA), providing fresh vegetables to partially fulfill city residents’ dietary needs. General weather information in the form of timely forecasts is insufficient to anticipate potential occurrences of weather types and features during the designated time windows for precise cultivation planning. In this research, we intended to use a self-organizing map (SOM), which is a clustering technique with powerful feature extraction ability to reveal hidden patterns of datasets, to explore the represented spatiotemporal weather features of Taipei city based on the observed data of six key weather factors that were collected at five weather stations in northern Taiwan during 2014 and 2018. The weather types and features of duration and distribution for Taipei on a 10-day basis were specifically examined, indicating that weather types #2, #4, and #7 featured to manifest the dominant seasonal patterns in a year. The results can serve as practical references to anticipate upcoming weather types/features within designated time frames, arrange potential/further measures of cultivation tasks and/or adjustments in response, and use water/energy resources efficiently for the sustainable production of smart urban agriculture.

Artificial Intelligence Techniques in Hydrology and Water Resources Management

“…Climate information can be utilized to help farmers plan their planting and production schedules, especially for urban agriculture. Huang and Chang used a self-organizing map (SOM) to investigate the spatiotemporal weather features of Taipei City by analyzing the observed data of six key weather factors from five weather stations in Northern Taiwan between 2014 and 2018 [26]. The results provide practical references for anticipating upcoming weather types and features within designated time frames, arranging potential cultivation tasks or making necessary adjustments, and efficiently utilizing water and energy resources to achieve sustainable production in smart urban agriculture.…”

Deep Architecture based on DenseNet-121 Model for Weather Image Recognition

“…The authors introduced a new dataset called the weather phenomenon database (WEAPD) that consists of 6,877 images for 11 different weather classes. Other researchers, such as Huang and Chang [23], employed a selforganizing map (SOM) to automatically classify weather images based on six variables at five different weather stations in Taiwan. Xia et al [24] modified ResNet-50 to ResNet-15 to classify weather images, where the convolutional layers extracted the weather features that would be fed into the softmax function for classification.…”

Develop a Smart Microclimate Control System for Greenhouses through System Dynamics and Machine Learning Techniques

“…Notes: 1 Amount of the traditional spraying system-amount of the SMCS. 2 Resource saving amount/amount of the traditional spraying system.…”

“…The huge agricultural loss caused by these extreme weather events accounted for 10.3% of the total value of agricultural production, resulting in severe fluctuations in food prices and disturbance in social equilibrium. Besides, changes in temperature and precipitation patterns may increase crop failures and production declines [2].…”