Hyperspectral imagery applications for precision agriculture - a systemic survey

Applications of optical sensing and imaging spectroscopy in indoor farming: A systematic review

As demand for food continues to rise, innovative methods are needed to sustainably and efficiently meet the growing pressure on agriculture. Indoor farming and controlled environment agriculture have emerged as promising approaches to address this challenge. However, optimizing fertilizer usage, ensuring homogeneous production, and reducing agro-waste remain substantial challenges in these production systems. One potential solution is the use of optical sensing technology, which can provide real-time data to help growers make informed decisions and enhance their operations. optical sensing can be used to analyze plant tissues, evaluate crop quality and yield, measure nutrients, and assess plant responses to stress. This paper presents a systematic literature review of the current state of using spectral-optical sensors and hyperspectral imaging for indoor farming, following the PRISMA 2020 guidelines. The study surveyed existing studies from 2017 to 2023 to identify gaps in knowledge, provide researchers and farmers with current trends, and offer recommendations and inspirations for possible new research directions. The results of this review will contribute to the development of sustainable and efficient methods of food production.

Tracing pistachio nuts' origin and irrigation practices through hyperspectral imaging

Pistachio trees have become a significant global agricultural commodity because their nuts are renowned for their unique flavour and numerous health benefits, contributing to their high demand worldwide. This study explores the application of Hyperspectral Imaging (HSI) and Machine Learning (ML) to determine pistachio nuts' geographic origin and irrigation practices, alongside predicting essential commercial quality and yield parameters. The study was conducted in two Spanish orchards and employed HSI technology to capture spectral data. It used ML models like Partial Least Squares (PLS), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost) for analysis. The results demonstrated high accuracy in classifying pistachios based on origin, with accuracies exceeding 94%, and in assessing water content and colour pigments, where both PLS and SVM models achieved 99% accuracy. The research highlighted distinct spectral signatures associated with different irrigation treatments, particularly in the Near-Infrared (NIR) region, with PLS showing an accuracy of 92%. However, challenges were noted in predicting fruit orientation, while predicting height location within the tree was more successful, reflecting clearer spectral distinctions. Regression models also showed promise, particularly in predicting yield (R2 = 0.89 with PLS) and percentage of blank nuts (R2 = 0.71 with PLS). The correlation analysis revealed key insights, such as an inverse relationship between blank nuts and yield, and a strong correlation between yield and split nuts. Despite challenges in predicting fruit orientation, the research showed promising results in forecasting yield and commercial quality factors, indicating the effectiveness of spectral analysis in optimising pistachio production and sustainability.

Enhancing Water-Deficient Potato Plant Identification: Assessing Realistic Performance of Attention-Based Deep Neural Networks and Hyperspectral Imaging for Agricultural Applications

Hyperspectral imaging has emerged as a pivotal technology in agricultural research, offering a powerful means to non-invasively monitor stress factors, such as drought, in crops like potato plants. In this context, the integration of attention-based deep learning models presents a promising avenue for enhancing the efficiency of stress detection, by enabling the identification of meaningful spectral channels. This study assesses the performance of deep learning models on two potato plant cultivars exposed to water-deficient conditions. It explores how various sampling strategies and biases impact the classification metrics by using a dual-sensor hyperspectral imaging systems (VNIR -Visible and Near-Infrared and SWIR-Short-Wave Infrared). Moreover, it focuses on pinpointing crucial wavelengths within the concatenated images indicative of water-deficient conditions. The proposed deep learning model yields encouraging results. In the context of binary classification, it achieved an area under the receiver operating characteristic curve (AUC-ROC-Area Under the Receiver Operating Characteristic Curve) of 0.74 (95% CI: 0.70, 0.78) and 0.64 (95% CI: 0.56, 0.69) for the KIS Krka and KIS Savinja varieties, respectively. Moreover, the corresponding F1 scores were 0.67 (95% CI: 0.64, 0.71) and 0.63 (95% CI: 0.56, 0.68). An evaluation of the performance of the datasets with deliberately introduced biases consistently demonstrated superior results in comparison to their non-biased equivalents. Notably, the ROC-AUC values exhibited significant improvements, registering a maximum increase of 10.8% for KIS Krka and 18.9% for KIS Savinja. The wavelengths of greatest significance were observed in the ranges of 475-580 nm, 660-730 nm, 940-970 nm, 1420-1510 nm, 1875-2040 nm, and 2350-2480 nm. These findings suggest that discerning between the two treatments is attainable, despite the absence of prominently manifested symptoms of drought stress in either cultivar through visual observation. The research outcomes carry significant implications for both precision agriculture and potato breeding. In precision agriculture, precise water monitoring enhances resource allocation, irrigation, yield, and loss prevention. Hyperspectral imaging holds potential to expedite drought-tolerant cultivar selection, thereby streamlining breeding for resilient potatoes adaptable to shifting climates.

A critical systematic review on spectral-based soil nutrient prediction using machine learning

The United Nations (UN) emphasizes the pivotal role of sustainable agriculture in addressing persistent starvation and working towards zero hunger by 2030 through global development. Intensive agricultural practices have adversely impacted soil quality, necessitating soil nutrient analysis for enhancing farm productivity and environmental sustainability. Researchers increasingly turn to Artificial Intelligence (AI) techniques to improve crop yield estimation and optimize soil nutrition management. This study reviews 155 papers published from 2014 to 2024, assessing the use of machine learning (ML) and deep learning (DL) in predicting soil nutrients. It highlights the potential of hyperspectral and multispectral sensors, which enable precise nutrient identification through spectral analysis across multiple bands. The study underscores the importance of feature selection techniques to improve model performance by eliminating redundant spectral bands with weak correlations to targeted nutrients. Additionally, the use of spectral indices, derived from mathematical ratios of spectral bands based on absorption spectra, is examined for its effectiveness in accurately predicting soil nutrient levels. By evaluating various performance measures and datasets related to soil nutrient prediction, this paper offers comprehensive insights into the applicability of AI techniques in optimizing soil nutrition management. The insights gained from this review can inform future research and policy decisions to achieve global development goals and promote environmental sustainability.

Histological Hyperspectral Glioblastoma Dataset (HistologyHSI-GB)

Hyperspectral (HS) imaging (HSI) technology combines the main features of two existing technologies: imaging and spectroscopy. This allows to analyse simultaneously the morphological and chemical attributes of the objects captured by a HS camera. In recent years, the use of HSI provides valuable insights into the interaction between light and biological tissues, and makes it possible to detect patterns, cells, or biomarkers, thus, being able to identify diseases. This work presents the HistologyHSI-GB dataset, which contains 469 HS images from 13 patients diagnosed with brain tumours, specifically glioblastoma. The slides were stained with haematoxylin and eosin (H&E) and captured using a microscope at 20× power magnification. Skilled histopathologists diagnosed the slides and provided image-level annotations. The dataset was acquired using custom HSI instrumentation, consisting of a microscope equipped with an HS camera covering the spectral range from 400 to 1000 nm.

Lightweight 3D Dense Autoencoder Network for Hyperspectral Remote Sensing Image Classification

The lack of labeled training samples restricts the improvement of Hyperspectral Remote Sensing Image (HRSI) classification accuracy based on deep learning methods. In order to improve the HRSI classification accuracy when there are few training samples, a Lightweight 3D Dense Autoencoder Network (L3DDAN) is proposed. Structurally, the L3DDAN is designed as a stacked autoencoder which consists of an encoder and a decoder. The encoder is a hybrid combination of 3D convolutional operations and 3D dense block for extracting deep features from raw data. The decoder composed of 3D deconvolution operations is designed to reconstruct data. The L3DDAN is trained by unsupervised learning without labeled samples and supervised learning with a small number of labeled samples, successively. The network composed of the fine-tuned encoder and trained classifier is used for classification tasks. The extensive comparative experiments on three benchmark HRSI datasets demonstrate that the proposed framework with fewer trainable parameters can maintain superior performance to the other eight state-of-the-art algorithms when there are only a few training samples. The proposed L3DDAN can be applied to HRSI classification tasks, such as vegetation classification. Future work mainly focuses on training time reduction and applications on more real-world datasets.

High-throughput phenotyping for non-destructive estimation of soybean fresh biomass using a machine learning model and temporal UAV data

BACKGROUND

Biomass accumulation as a growth indicator can be significant in achieving high and stable soybean yields. More robust genotypes have a better potential for exploiting available resources such as water or sunlight. Biomass data implemented as a new trait in soybean breeding programs could be beneficial in the selection of varieties that are more competitive against weeds and have better radiation use efficiency. The standard techniques for biomass determination are invasive, inefficient, and restricted to one-time point per plot. Machine learning models (MLMs) based on the multispectral (MS) images were created so as to overcome these issues and provide a non-destructive, fast, and accurate tool for in-season estimation of soybean fresh biomass (FB). The MS photos were taken during two growing seasons of 10 soybean varieties, using six-sensor digital camera mounted on the unmanned aerial vehicle (UAV). For model calibration, canopy cover (CC), plant height (PH), and 31 vegetation index (VI) were extracted from the images and used as predictors in the random forest (RF) and partial least squares regression (PLSR) algorithm. To create a more efficient model, highly correlated VIs were excluded and only the triangular greenness index (TGI) and green chlorophyll index (GCI) remained.

RESULTS

More precise results with a lower mean absolute error (MAE) were obtained with RF (MAE = 0.17 kg/m2) compared to the PLSR (MAE = 0.20 kg/m2). High accuracy in the prediction of soybean FB was achieved using only four predictors (CC, PH and two VIs). The selected model was additionally tested in a two-year trial on an independent set of soybean genotypes in drought simulation environments. The results showed that soybean grown under drought conditions accumulated less biomass than the control, which was expected due to the limited resources.

CONCLUSION

The research proved that soybean FB could be successfully predicted using UAV photos and MLM. The filtration of highly correlated variables reduced the final number of predictors, improving the efficiency of remote biomass estimation. The additional testing conducted in the independent environment proved that model is capable to distinguish different values of soybean FB as a consequence of drought. Assessed variability in FB indicates the robustness and effectiveness of the proposed model, as a novel tool for the non-destructive estimation of soybean FB.

A Band Selection Approach for Hyperspectral Image Based on a Modified Hybrid Rice Optimization Algorithm

Hyperspectral image (HSI) analysis has become one of the most active topics in the field of remote sensing, which could provide powerful assistance for sensing a larger-scale environment. Nevertheless, a large number of high-correlation and redundancy bands in HSI data provide a massive challenge for image recognition and classification. Hybrid Rice Optimization (HRO) is a novel meta-heuristic, and its population is approximately divided into three groups with an equal number of individuals according to self-equilibrium and symmetry, which has been successfully applied in band selection. However, there are some limitations of primary HRO with respect to the local search for better solutions and this may result in overlooking a promising solution. Therefore, a modified HRO (MHRO) based on an opposition-based-learning (OBL) strategy and differential evolution (DE) operators is proposed for band selection in this paper. Firstly, OBL is adopted in the initialization phase of MHRO to increase the diversity of the population. Then, the exploitation ability is enhanced by embedding DE operators into the search process at each iteration. Experimental results verify that the proposed method shows superiority in both the classification accuracy and selected number of bands compared to other algorithms involved in the paper.

High-Precision Seedling Detection Model Based on Multi-Activation Layer and Depth-Separable Convolution Using Images Acquired by Drones

Crop seedling detection is an important task in the seedling stage of crops in fine agriculture. In this paper, we propose a high-precision lightweight object detection network model based on a multi-activation layer and depth-separable convolution module to detect crop seedlings, aiming to improve the accuracy of traditional artificial intelligence methods. Due to the insufficient dataset, various image enhancement methods are used in this paper. The dataset in this paper was collected from Shahe Town, Laizhou City, Yantai City, Shandong Province, China. Experimental results on this dataset show that the proposed method can effectively improve the seedling detection accuracy, with the F1 score and mAP reaching 0.95 and 0.89, respectively, which are the best values among the compared models. In order to verify the generalization performance of the model, we also conducted a validation on the maize seedling dataset, and experimental results verified the generalization performance of the model. In order to apply the proposed method to real agricultural scenarios, we encapsulated the proposed model in a Jetson logic board and built a smart hardware that can quickly detect seedlings.