農業物聯網技術整合之研究‒以設施農業施作與病蟲害管理為例

Study on the Integration of Agricultural Internet of Things: Practical Cases of Facility Agriculture and Pest Management

廖敏勝(Min-Sheng Liao)

指導教授 ： 江昭皚

國立臺灣大學/生物資源暨農學院/生物產業機電工程學研究所/博士(2017年)

https://doi.org/10.6342/NTU201702889

摘要

物聯網於近年來開始蓬勃發展，為人類帶來一個資訊透明與快速交換的世界。物聯網可實現智能化識別、資訊管理並融入各種應用當中。各產業無不想方設法導入物聯網，藉以降低成本、提升產品品質與產量，進而增加產業價值。舉例而言，近年來，農業因氣候環境變遷以及食品安全等議題，持續地被世人關注，世界各國無不在考量在農業發展上，可否用更具效率以及安全的方式生產，同時解決農業糧食問題與提升農產品價值。利用物聯網技術打造智慧農業，提供了一個兩全其美的解決方案。本論文提出多個農業物聯網之應用案例，包含設施農業與病蟲害管理，內容闡述如何依照各案例之需求提出解決方案，並分析其效益。
在設施農業上，本論文實際設置一套物聯網監測系統於蘭花溫室與植物工廠中。在蘭花溫室中，本論文可成功監測與分析蘭花生長環境與蘭花葉面積生長情況。根據分析結果，可得知蘭花處於高濕度之環境，其葉面積成長較緩慢，進而影響開花品質。藉由物聯網系統所提供之量化數據與結果，可有效幫助蘭花業者計畫耕種策略。在植物工廠中，本論文可即時偵測區域高溫，並對其進行通風，有效地提升波士頓萵苣之鮮重以及銷售價格。
在病蟲害管理上，本論文亦實際設置多套物聯網監測系統於臺灣各地之重要蔬果產區，並監測多種害蟲，包含東方果實蠅與斜紋夜蛾。此物聯網監測系統可監測該果園受到東方果實蠅或斜紋夜蛾之危害的程度，並利用自組織映射圖網路建立資料分類模型。實驗結果顯示資料分類模型，對檢測事件類型的判定效果極佳，有助於系統鑑別該果園是否達蟲害爆發之程度，以及感測資料是否異常或發生故障。相較於現有之人工定時監測方式，本論文可有效提升監測時空解析度。

關鍵字

智慧農業 ； 農業物聯網 ； 設施農業 ； 植物病蟲害管理

並列摘要

Recently, Internet of things (IoT) technologies have been rapidly developed. IoTs create a new world which is transparent with faster speeds of information flows and innovation. IoTs are able to implement intelligent identification and information management, and they can be integrated to various applications. All industries try to employ IoT technologies to reduce labor costs, improve the quality and yield of products, and increase the value of their industries. For example, in recent years, agricultural issues have continuously gained attention from humans. All countries in the world are considering the development of agriculture, and wondering if food can be produced in more efficient and safe ways by putting their effort on improving agricultural food safety and enhancing the value of agricultural products. Smart agriculture that utilizes IoT technologies provides an excellent solution. This paper presents serval agricultural IoT applications in facility agriculture and pest management. The paper describes the solutions in accordance with the demand of each case and analyzes the benefits of using the IoT applications.
In the applications of facility agriculture, this paper actually deployed an IoT-based monitoring system in an orchid greenhouse and plant factories. In the greenhouse, for example, this paper has successfully monitored the growth of orchids and analyzed the relations between the environment factors and the growth of orchid leaf areas. The analyzed results indicate that the growth of the areas would slow down in a highly humid environment, thereby influenced the blossom quality. And, the analyzed results provided by the IoT-based monitoring system can help greenhouse owners update their farming strategies.
For plant factories, an IoT-based monitoring system was able to detect and ventilate local high temperature areas in plant factories. The analyzed results indicate that the fresh weights and sales of the Boston lettuce both increased while the proposed IoT-based monitoring system was used in the plant factories.
For pest management, this paper has also actually deployed serval IoT-based monitoring systems in orchards and vegetable producing areas around Taiwan to monitor the population of different insect pests, including the oriental fruit fly (Bactrocera dorsalis) and tobacco cutworm (Spodoptera litura). The IoT-based monitoring system can monitor the oriental fruit fly or the tobacco cutworm in orchards or vegetable producing areas by using self-organizing maps to establish classification models. The experimental results show that the efficiency of the classification models was excellent, and the models can help the monitoring system identify whether a pest outbreak event or an error in the monitoring data occurs. Compared to traditional monitoring methods, the proposed IoT-based monitoring system can efficiently improve temporal and spatial resolutions of monitoring and reduce labor costs.

並列關鍵字

Smart agriculture ； Agricultural Internet of things ； Facility agriculture ； Pest management

參考文獻

Mohamed, M. S., and T. Kavitha. 2011. Outlier detection using support vector machine in wireless sensor network real time data. Int. J. Soft Comput. Eng. 1(2): 68–72.

Chen, C. P., C. L. Chuang, C. L. Tseng, E. C. Yang, M. Y. Liu, and J. A. Jiang. 2009. A novel energy efficient adaptive routing protocol for wireless sensor networks. J. Chin. Soc. Mech. Eng. 30(1): 59–65.

Lee, N., and M. C. Wang. 1997. Changes in mineral composition and carbohydrate contents from juvenile to mature phase in white-flowered Phalaenopsis plants. J. Chinese Soc. Hort. Sci. 43: 295−305. (in Chinese with English abstract)

Lin, G. M., and N. Lee. 1988. Leaves area estimation and the effect of temperature on the growth of Phalaenopsis leaves. J. Chinese Soc. Hort. Sci. 34: 73−80. (in Chinese with English abstract)

Chang, Y. C., C. Y. Lee, X. Y. Zheng, and C. L. Chuang. 2012. A data retransmitting mechanism for ecological monitoring system. In “Proc. the 2012 Fifth IEEE International Conference on Service-Oriented Computing and Applications (SOCA)”, pp. 1−6.