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%.

Agricultural Remote Sensing has the potential to enhance agricultural monitoring in smallholder economies to mitigate losses. However, its widespread adoption faces challenges, such as diminishing farm sizes, lack of reliable data-sets and high cost related to commercial satellite imagery. This research focuses on opportunities, practices and novel approaches for effective utilization of remote sensing in agriculture applications for smallholder economies. The work entails insights from experiments using datasets representative of major crops during different growing seasons. We propose an optimized solution for addressing challenges associated with remote sensing-based crop mapping in smallholder agriculture farms. Open source tools and data are used for inter and intra-sensor image registration, with a root mean square error of 0.3 or less. We also propose and emphasize on the use of delineated vegetation parcels through Segment Anything Model for Geospatial (SAM-GEOs). Furthermore a Bidirectional-Long Short-Term Memory-based (Bi-LSTM) deep learning model is developed and trained for crop classification, achieving results with accuracy of more than 94% and 96% for validation sets of two data sets collected in the field, during 2 growing seasons.

This study aimed to develop a new method for combining Sentinel-2 and PlanetScope imagery. The normalized difference vegetation indices (NDVI) data were retrieved from the Earth observation satellites S2 Level-2A and PS Level-3 surface reflectance (PS) during the soybean growing phase. The proposed method utilizes the pyDMS algorithm, which is a decision tree-based technique for enhancing low and high-resolution images with information from large-scale images. The robustness and flexibility of a multidimensional data fusion, deep neural network, and machine learning-based yield estimation model were analyzed based on the within-field variability in soybean yield. A comparative analysis revealed that the fusion data with 1.5 to 2.5 tons significantly outperformed individual predictions, demonstrating higher accuracy and fewer errors. The fusion data used to predict yields showed relatively small error ranges of 0.5 to 0.2 t/ha. In contrast, the PS and S2 datasets showed higher prediction errors. The study employed vegetation indices, and during validation, crop forecasts were compared using an NDVI map. The effectiveness of artificial neural networks in predicting crop yields was highlighted, demonstrating superior performance across diverse datasets compared with other algorithms. This novel fusion technique is essential for monitoring crop health and growth, improving agricultural practices, such as fertilization and water management, and improving yield forecast accuracy. This study provides valuable insights into phenology monitoring, image fusion accuracy, and the effectiveness of machine learning algorithms in predicting crop yields, emphasizing the benefits of fused imagery.

Deep learning (DL) has seen a massive rise in popularity for remote sensing (RS) based applications over the past few years. However, the performance of DL algorithms is dependent on the optimization of various hyperparameters since the hyperparameters have a huge impact on the performance of deep neural networks. The impact of hyperparameters on the accuracy and reliability of DL models is a significant area for investigation. In this study, the grid Search algorithm is used for hyperparameters optimization of long short-term memory (LSTM) network for the RS-based classification. The hyperparameters considered for this study are, optimizer, activation function, batch size, and the number of LSTM layers. In this study, over 1,000 hyperparameter sets are evaluated and the result of all the sets are analyzed to see the effects of various combinations of hyperparameters as well the individual parameter effect on the performance of the LSTM model. The performance of the LSTM model is evaluated using the performance metric of minimum loss and average loss and it was found that classification can be highly affected by the choice of optimizer; however, other parameters such as the number of LSTM layers have less influence.

Deep learning (DL) techniques are effective in various applications, such as parameter estimation, image classification, recognition, and anomaly detection. They excel with abundant training data but struggle with limited data. To overcome this, transfer learning is commonly used, leveraging complex learning abilities, saving time, and handling limited labeled data. This study assesses a transfer learning (TL)-based pre-trained “deep convolutional neural network (DCNN)” for classifying land use land cover using a limited and imbalanced dataset of fused spectro-temporal data. It compares the performance of shallow artificial neural networks (ANNs) and deep convolutional neural networks, utilizing multi-spectral sentinel-2 and high-resolution planet scope data. Both machine learning and deep learning algorithms successfully classified the fused data, but the transfer learning-based deep convolutional neural network outperformed the artificial neural network. The evaluation considered a weighted average of F1-score and overall classification accuracy. The transfer learning-based convolutional neural network achieved a weighted average F1-score of 0.92 and a classification accuracy of 0.93, while the artificial neural network achieved a weighted average F1-score of 0.87 and a classification accuracy of 0.89. These results highlight the superior performance of the transfer learned convolutional neural network on a limited and imbalanced dataset compared to the traditional artificial neural network algorithm.

Crop classification and its area estimation hold significant importance in agricultural production and management. It serves as a crucial tool for efficiently identifying various crops and contributes to the formulation of tailored strategies for crop-specific production and estimation purposes. Numerous deep learning techniques, with a particular emphasis on Convolutional Neural Networks (CNNs), have found application in the analysis of satellite data for crop classification. Nevertheless, this approach has its limitations, notably the challenge of sequential information loss, which hinders its ability to accurately extract features that rely on temporal changes over time. On the other hand, another deep learning technique, the Gated Recurrent Unit (GRU), excels at handling time series data but falls short in its ability to extract intricate patterns within the data, a strength of CNNs. This study explores the capabilities of these methodologies for crop classification in the Charsadda district of Pakistan, a region renowned for its diverse agricultural landscape dedicated to the cultivation of economically valuable crops. We introduce a dual-channel CNN-GRU feature fusion architecture, a method that merges individually extracted features from both CNNs and GRUs. The proposed framework is specifically designed for data obtained from Sentinel-2 and PlanetScope imagery, complemented by NDVI time series data collected from the study site. The model’s performance is assessed in comparison to the individual performance of CNN and GRU models. The models were subjected to evaluation using a variety of metrics, encompassing precision, recall, F1 Score, and overall accuracy. The outcomes reveal that the proposed model surpasses the performance of the individual models. The feature fusion-based model emerged as the top performer, achieving an overall accuracy of 96.47 percent, an F1 Score of 93.16 percent, a precision of 93.93 percent, and a recall of 92.69 percent. This research offers substantial evidence supporting the potential of the CNN-GRU feature fusion model for crop identification. By harnessing the strengths of both architectural approaches, it demonstrates its effectiveness as a valuable tool for crop classification.