A Short Survey of Hyperspectral Remote Sensing Applications in Agriculture Mustafa Teke 1 , Hüsne Seda Deveci 1 , Onur Haliloğlu 1 , Sevgi Zübeyde Gürbüz 1,2 , Ufuk Sakarya 1 1 TÜBİTAK UZAY (The Scientific and Technological Research Council of Turkey, Space Technologies Research Institute) ODTÜ Yerleşkesi, 06531, Ankara, Turkey 2 TOBB University of Economics and Technology, Dept. of Electrical-Electronics Eng., Ankara, Turkey {mustafa.teke, seda.deveci, onur.haliloglu, sevgi.gurbuz, ufuk.sakarya}@tubitak.gov.tr Abstract—Hyperspectral sensors are devices that acquire images over hundreds of spectral bands, thereby enabling the extraction of spectral signatures for objects or materials observed. Hyperspectral remote sensing has been used over a wide range of applications, such as agriculture, forestry, geology, ecological monitoring and disaster monitoring. In this paper, the specific application of hyperspectral remote sensing to agriculture is examined. The technological development of agricultural methods is of critical importance as the world’s population is anticipated to continuously rise much beyond the current number of 7 billion. One area upon which hyperspectral sensing can yield considerable impact is that of precision agriculture – the use of observations to optimize the use of resources and management of farming practices. For example, hyperspectral image processing is used in the monitoring of plant diseases, insect pests and invasive plant species; the estimation of crop yield; and the fine classification of crop distributions. This paper also presents a detailed overview of hyperspectral data processing techniques and suggestions for advancing the agricultural applications of hyperspectral technologies in Turkey. Keywords—survey; hyperspectral image processing; remote sensing; precision agriculture. I. INTRODUCTION Since the successful launch and deployment of the first experimental satellite, Sputnik, in 1957, satellites have been used for applications such as surveillance, navigation, communication, remote sensing, and earth observation. Notable applications to remote sensing include those relating to meteorology, agriculture, mining, geology, mapping, city planning, ecological monitoring and disaster monitoring. Although primarily electro-optical visible sensors have been used, more recently, the application of thermal imagers, synthetic aperture radar (SAR), light detection and ranging (LIDAR), and hyperspectral imagers has gained increasing attention. Hyperspectral remote sensing is defined as the simultaneous acquisition of images in many narrow, contiguous spectral bands [1]. Hyperspectral sensors are specially designed devices capable of acquiring detailed images of observed objects of hundreds of narrow spectral bands. The spectral signatures extractable from the hyperspectral image cube can used to classify or recognize objects, materials, or areas of the region viewed. Typically, hyperspectral imaging devices capture light in the range of 400 nm – 2500 nm, covering the visible, near infrared (NIR), and short wave infrared (SWIR) frequency bands. While multispectral data is acquired over a relatively small number (<10) of broad spectral bands (≈ 100 nm band width), hyperspectral imagers acquire data over numerous (tens to hundreds) narrow (< 20 nm) spectral bands. Spaceborne systems tend to have a lower spatial resolution (30-150 m) in comparison to their airborne counterparts (35 cm – 4 m) [2]. One important application of hyperspectral imaging technologies is that of agriculture, and in particular, precision agriculture. Precision agriculture can be broadly defined as the use of observations to optimize the use of resources and management of farming practices. Typically, a ground positioning system (GPS) combined with the readings from other geographical information systems (GIS), including satellite data, is used to monitor the crops, manage the use of resources, and make decisions on farming practices. An example of sensor usage includes the determination of soil characteristics, such as texture, structure, physical character, humidity, and nutrient level. This paper examines the application of hyperspectral imagers to precision agriculture. In Section II, details about hyperspectral sensing technologies are given. Section III discusses agricultural applications of hyperspectral imaging, focusing on the monitoring of plants and insects, crop yield estimation, and crop classification. Hyperspectral data processing techniques, such as dimension reduction/band selection, classification/clustering, spectral libraries, and radiometric calibration/correction, is detailed in Section IV. Finally, in Section V, conclusions are given in addition to suggestions for the advancement of hyperspectral technology use for precision agriculture in Turkey. II. HYPERSPECTRAL SENSORS AND IMAGE PROCESSING Hyperspectral sensors, also referred to as imaging spectrometers, represent the next step in spectral imaging beyond that of multispectral imaging radiometers, current spaceborne examples of which include, LANDSAT, SPOT, IKONOS and WorldView. Spectral imaging involves the collection of multiple images over multiple wavelength bands. The data is aligned in such a way that each spatial location, or pixel, contains data for all measured wavelengths. Thus, hyperspectral images are in fact a three-dimensional cube of data (Figure 1). The X and Y axis specify the dimensions of the images, while the Z axis denotes the spectral wavelength. The value of each pixel in the image is spectral reflectance, the amount of optical energy received by the sensor from the sun after reflecting from the Earth’s surface. The value of hyperspectral sensing lies in its ability to capture information