On the Performance of Temporal Stacking and Vegetation Indices for Detection and Estimation of Tobacco Crop

Abstract

Machine learning in association with remote sensing has assisted agricultural specialists in monitoring, classification and yield estimation of crops. Tobacco is a major taxable crop of Pakistan, however the existing traditional methods for its monitoring and yield estimation are not only expensive and time consuming but also have limitations in terms of accuracy of collected data by a large number of diverse human surveyors. Due to the existence of such loopholes in the employed mechanism for tobacco crop monitoring and yield estimation, its illicit growth and distribution is on the rise. In this paper we have established a sophisticated machine learning mechanism for tobacco crop estimation using temporally stacked sentinel-2 satellite's data of Pakistan. Instead of the conventional approach of using single remotely sensed imagery for the target crop classification, we propose a machine learning based classification algorithm while keeping in view the phonological cycle of the target tobacco crop. Using the proposed mechanism, the temporal variations within the tobacco crop and its association with the variations of other vegetation is considered to improve the classification performance of the employed machine learning algorithm. Furthermore, the impact of stacking the vegetation indices derived from near infrared and vegetation red edge bands of sentinel-2 with the original sentinel-2 datasets, including Normalized Difference Vegetation Index (NDVI) and Normalized Difference Index 45 (NDI45), on the classification performance of the machine learning mechanism is investigated. Ground Truth data for training of our Artificial Neural Networks classifier, was obtained using indigenously developed survey application "GEOSurvey". Experiments were conducted using our proposed mechanism while considering various input data setups-including single date imagery, temporally stacked datasets based on phonological cycle of tobacco crop and different combinations of NDVI and NDI45 stacking. Our proposed experimental setup consisting of temporally stacked imagery along with NDVI stacking results in the best classification performance of 95.81% with reference to the single date imagery stacked with NDVI and NDI45, with performance gain of 07.32%.

Rice False Smut Detection and Prescription Map Generation in a Complex Planting Environment, with Mixed Methods, Based on Near Earth Remote Sensing

“…Fewer studies on RFS have been based on near earth remote sensing. A large number of researchers have emphasized other crop diseases, such as satellite remote sensing for wheat Fusarium head blight [8], soybean sudden death syndrome [9], tobacco crop [10], rice bacterial leaf blight [11], soybean sudden death syndrome [12], near earth remote sensing for cucumber leaves in response to angular leaf spot disease [13], early disease in wheat fields [14], watermelon disease detection [15], rye leaf rust symptoms [16], paddy leaf disease [17], onion purple blotch [18], etc.…”

Finding a suitable sensing time period for crop identification using heuristic techniques with multi-temporal satellite images

“…These conditioning factors imply the presence of strict controls. Tobacco detection has been recently treated with different approaches, using near-infrared spectroscopy sensors (D. Jiang et al 2020;Wang et al 2018) or satellite images (Khan et al 2020;Minallah et al 2020), which emphasizes its importance.…”

On the performance of fusion based planet-scope and Sentinel-2 data for crop classification using inception inspired deep convolutional neural network

“…The ground data collection surveys of the pilot region were conducted using an indigenously developed Geo Survey application [23]. A brief overview of the Geo Survey application is pictorially presented in (Fig 3) [7]. (Fig 3(a)) presents the main view of the application, with multiple choices to choose the method of survey.…”

“…This section presents parameters on which classification performance has been evaluated [7] and classification report of the proposed model over the pilot region.…”

“…They have shown promising performance in diverse fields such as automatic decision support in medical diagnosis and classification of archaeological artifacts [5,6]. In [7] the use of temporal features for Tobacco crop estimation and detection using feed forward neural network resulted in the achievement of more than 95% accuracy.…”