Accurate detection of drought stress in plants is essential for water use efficiency and agricultural output. Hyperspectral imaging (HSI) provides a non-invasive method in plant phenotyping, allowing the long-term monitoring of plant health due to sensitivity to subtle changes in leaf constituents. The broad spectral range of HSI enables the development of different vegetation indices (VIs) to analyze plant trait responses to multiple stresses, such as the combination of nutrient and drought stresses. However, known VIs may underperform when subjected to multiple stresses. This study presents new VIs in tandem with machine learning models to identify drought stress in wheat plants under varying nitrogen (N) levels. A pot wheat experiment was set up in the glasshouse with four treatments: well-watered high-N (WWHN), well-watered low-N (WWLN), drought-stress high-N (DSHN) and drought-stress low-N (DSLN). In addition to ensuring that plants were watered according to the experiment design, photosynthetic rate (P_n) and stomatal conductance (g_s) (which are used to assess plant drought stress) were taken regularly, serving as the ground truth data for this study. The proposed VIs, together with known VIs, were used to train three classification models: support vector machines (SVM), random forest (RF), and deep neural networks (DNN) to classify plants based on their drought status. The proposed VIs achieved more than 0.94 accuracy across all models, and their performance further increased when combined with known VIs. The combined VIs were used to train three regression models to predict the stomatal conductance and photosynthetic rates of plants. The random forest regression model performed best, suggesting that it could be used as a stand-alone tool to forecast g_s and P_n and track drought stress in wheat. This study shows that combining hyperspectral data with machine learning can effectively monitor and predict drought stress in crops, especially in varying nitrogen conditions.

Artisanal gold mining (galamsey) and cocoa farming are essential sources of income for local populations in Ghana. Unfortunately the former poses serious threats to the environment and human health, and conflicts with cocoa farming and other livelihoods. Timely and spatially referenced information on the extent of galamsey is needed to understand and limit the negative impacts of mining. To address this, we use multi-date UK-DMC2 satellite images to map the extent and expansion of galamsey from 2011 to 2015. We map the total area of galamsey in 2013 over the cocoa growing area, using k-means clustering on a cloud-free 2013 image with strong spectral contrast between galamsey and the surrounding vegetation. We also process a pair of hazy images from 2011 and 2015 with Multivariate Alteration Detection to map the 2011–2015 galamsey expansion in a subset, labelled the change area. We use a set of visually interpreted random sample points to compute bias-corrected area estimates. We also delineate an indicative impact zone of pollution proportional to the density of galamsey, assuming a maximum radius of 10 km. In the cocoa growing area of Ghana, the estimated total area of galamsey in 2013 is 27,839 ha with an impact zone of 551,496 ha. In the change area, galamsey has more than tripled between 2011 and 2015, resulting in 603 ha of direct encroachment into protected forest reserves. Assuming the same growth rate for the rest of the cocoa growing area, the total area of galamsey in 2015 is estimated at 43,879 ha. Galamsey is developing along most of the river network (Offin, Ankobra, Birim, Anum, Tano), with downstream pollution affecting both land and water

Image segmentation is a fundamental but critical step for achieving automated high- throughput phenotyping. While conventional segmentation methods perform well in homogenous environments, the performance decreases when used in more complex environments. This study aimed to develop a fast and robust neural-network-based segmentation tool to phenotype plants in both field and glasshouse environments in a high-throughput manner. Digital images of cowpea (from glasshouse) and wheat (from field) with different nutrient supplies across their full growth cycle were acquired. Image patches from 20 randomly selected images from the acquired dataset were transformed from their original RGB format to multiple color spaces. The pixels in the patches were annotated as foreground and background with a pixel having a feature vector of 24 color properties. A feature selection technique was applied to choose the sensitive features, which were used to train a multilayer perceptron network (MLP) and two other traditional machine learning models: support vector machines (SVMs) and random forest (RF). The performance of these models, together with two standard color-index segmentation techniques (excess green (ExG) and excess green–red (ExGR)), was compared. The proposed method outperformed the other methods in producing quality segmented images with over 98%-pixel classification accuracy. Regression models developed from the different segmentation methods to predict Soil Plant Analysis Development (SPAD) values of cowpea and wheat showed that images from the proposed MLP method produced models with high predictive power and accuracy comparably. This method will be an essential tool for the development of a data analysis pipeline for high-throughput plant phenotyping. The proposed technique is capable of learning from different environmental conditions, with a high level of robustness.

An integrated application of remote-sensing technology was devised and applied in Afghanistan during 2003–2009 providing critical information on cereal and poppy cultivation and poppy eradication. The results influenced UK and international policy and counter-narcotics actions in Afghanistan.

We investigated and developed a prototype crop information system integrating 250 m Moderate Resolution Imaging Spectroradiometer (MODIS) normalized difference vegetation index (NDVI) data with other available remotely sensed imagery, field data, and knowledge as part of a wider project monitoring opium and cereal crops. NDVI profiles exhibited large geographical variations in timing, height, shape, and number of peaks, with characteristics determined by underlying crop mixes, growth cycles, and agricultural practices. MODIS pixels were typically bigger than the field sizes, but profiles were indicators of crop phenology as the growth stages of the main first-cycle crops (opium poppy and cereals) were in phase. Profiles were used to investigate crop rotations, areas of newly exploited agriculture, localized variation in land management, and environmental factors such as water availability and disease. Near-real-time tracking of the current years’ profile provided forecasts of crop growth stages, early warning of drought, and mapping of affected areas. Derived data products and bulletins provided timely crop information to the UK Government and other international stakeholders to assist the development of counter-narcotic policy, plan activity, and measure progress. Results show the potential for transferring these techniques to other agricultural systems.