Application of remote sensing technology to estimate productivity and assess phylogenetic heritability

Monitoring of Antarctica's Fragile Vegetation Using Drone-Based Remote Sensing, Multispectral Imagery and AI

Vegetation in East Antarctica, such as moss and lichen, vulnerable to the effects of climate change and ozone depletion, requires robust non-invasive methods to monitor its health condition. Despite the increasing use of unmanned aerial vehicles (UAVs) to acquire high-resolution data for vegetation analysis in Antarctic regions through artificial intelligence (AI) techniques, the use of multispectral imagery and deep learning (DL) is quite limited. This study addresses this gap with two pivotal contributions: (1) it underscores the potential of deep learning (DL) in a field with notably limited implementations for these datasets; and (2) it introduces an innovative workflow that compares the performance between two supervised machine learning (ML) classifiers: Extreme Gradient Boosting (XGBoost) and U-Net. The proposed workflow is validated by detecting and mapping moss and lichen using data collected in the highly biodiverse Antarctic Specially Protected Area (ASPA) 135, situated near Casey Station, between January and February 2023. The implemented ML models were trained against five classes: Healthy Moss, Stressed Moss, Moribund Moss, Lichen, and Non-vegetated. In the development of the U-Net model, two methods were applied: Method (1) which utilised the original labelled data as those used for XGBoost; and Method (2) which incorporated XGBoost predictions as additional input to that version of U-Net. Results indicate that XGBoost demonstrated robust performance, exceeding 85% in key metrics such as precision, recall, and F1-score. The workflow suggested enhanced accuracy in the classification outputs for U-Net, as Method 2 demonstrated a substantial increase in precision, recall and F1-score compared to Method 1, with notable improvements such as precision for Healthy Moss (Method 2: 94% vs. Method 1: 74%) and recall for Stressed Moss (Method 2: 86% vs. Method 1: 69%). These findings contribute to advancing non-invasive monitoring techniques for the delicate Antarctic ecosystems, showcasing the potential of UAVs, high-resolution multispectral imagery, and ML models in remote sensing applications.

What Can Evolutionary History Tell Us about the Functioning of Ecological Communities? The ASN Presidential Debate

AbstractIn January 2018, Sharon Strauss, then president of the American Society of Naturalists, organized a debate on the following topic: does evolutionary history inform the current functioning of ecological communities? The debaters-Ives, Lau, Mayfield, and Tobias-presented pro and con arguments, caricatured in standard debating format. Numerous examples show that both recent microevolutionary and longer-term macroevolutionary history are important to the ecological functioning of communities. On the other hand, many other examples illustrate that the evolutionary history of communities or community members does not influence ecological function, or at least not very much. This article aims to provide a provocative discussion of the consistent and conflicting patterns that emerge in the study of contemporary and historical evolutionary influences on community function, as well as to identify questions for further study. It is intended as a thought-provoking exercise to explore this complex field, specifically addressing (1) key assumptions and how they can lead us astray and (2) issues that need additional study. The debaters all agree that evolutionary history can inform us about at least some aspects of community function. The underlying question at the root of the debate, however, is how the fields of ecology and evolution can most profitably collaborate to provide a deeper and broader understanding of ecological communities.

Long-term evolution of quantitative traits in the Drosophila melanogaster species subgroup

Quantitative genetics aims at untangling the genetic and environmental effects on phenotypic variation. Trait heritability, which summarizes the relative importance of genetic effects, is estimated at the intraspecific level, but theory predicts that heritability could influence long-term evolution of quantitative traits. The phylogenetic signal concept bears resemblance to heritability and it has often been called species-level heritability. Under certain conditions, such as trait neutrality or contribution to phylogenesis, within-species heritability and between-species phylogenetic signal should be correlated. Here, we investigate the potential relationship between these two concepts by examining the evolution of multiple morphological traits for which heritability has been estimated in Drosophila melanogaster. Specifically, we analysed 42 morphological traits in both sexes on a phylogeny inferred from 22 nuclear genes for nine species of the melanogaster subgroup. We used Pagel's λ as a measurement of phylogenetic signal because it is the least influenced by the number of analysed taxa. Pigmentation traits showed the strongest concordance with the phylogeny, but no correlation was found between phylogenetic signal and heritability estimates mined from the literature. We obtained data for multiple climatic variables inferred from the geographical distribution of each species. Phylogenetic regression of quantitative traits on climatic variables showed a significantly positive correlation with heritability. Convergent selection, the response to which depends on the trait heritability, may have led to the null association between phylogenetic signal and heritability for morphological traits in Drosophila. We discuss the possible causes of discrepancy between both statistics and caution against their confusion in evolutionary biology.

Spatiotemporal Variation and Influencing Factors of Vegetation Growth in Mining Areas: A Case Study in a Colliery in Northern China

Based on MODIS EVI data of August collected from 2010 to 2021, and taking the Yingpanhao coal mine as an example, the spatiotemporal variation features of vegetation are analyzed using time series analysis, trend analysis and correlation analysis methods in the eco-geo-environment of the phreatic water desert shallows oasis. A significant increase trend is found for vegetation variation, and its development has improved generally in most areas. There is an obvious positive correlation between precipitation and vegetation growth, and a negative correlation between coal mining intensity and vegetation growth, but the influence of atmospheric precipitation on vegetation growth is stronger than that of coal mining intensity in the eco-geo-environment. The research results effectively reflect that atmospheric precipitation is the primary factor advancing the vegetation growth status in the coal mining regions. Vegetation development response to coal mining would be degraded first, then improved, and finally restored in areas with a deeply buried phreatic water level; that would promote the transformation of vegetation species from hydrophilous plants to xerophyte plants in areas with a shallowly buried phreatic water level. Therefore, it is necessary to carry out reasonable mine field planning according to the phreatic water level and the vegetation type distribution and to adopt different coal mining methods or corresponding engineering and technical measures to realize water conservation to avoid damaging the original hydrogeological conditions as far as possible. This information is helpful for promoting the eco-geo-environmental protection and further establishing the need for the dynamic monitoring of the eco-environment in the coal mining regions in the arid and semi-arid ecologically vulnerable areas of Northern China, which play a significant role in the long-term protection and rehabilitation of the eco-geo-environment and in the promotion of sustainable development.

Optimizing process-based models to predict current and future soil organic carbon stocks at high-resolution

From hillslope to small catchment scales (< 50 km²), soil carbon management and mitigation policies rely on estimates and projections of soil organic carbon (SOC) stocks. Here we apply a process-based modeling approach that parameterizes the MIcrobial-MIneral Carbon Stabilization (MIMICS) model with SOC measurements and remotely sensed environmental data from the Reynolds Creek Experimental Watershed in SW Idaho, USA. Calibrating model parameters reduced error between simulated and observed SOC stocks by 25%, relative to the initial parameter estimates and better captured local gradients in climate and productivity. The calibrated parameter ensemble was used to produce spatially continuous, high-resolution (10 m²) estimates of stocks and associated uncertainties of litter, microbial biomass, particulate, and protected SOC pools across the complex landscape. Subsequent projections of SOC response to idealized environmental disturbances illustrate the spatial complexity of potential SOC vulnerabilities across the watershed. Parametric uncertainty generated physicochemically protected soil C stocks that varied by a mean factor of 4.4 × across individual locations in the watershed and a − 14.9 to + 20.4% range in potential SOC stock response to idealized disturbances, illustrating the need for additional measurements of soil carbon fractions and their turnover time to improve confidence in the MIMICS simulations of SOC dynamics.

Predicting Canopy Chlorophyll Content in Sugarcane Crops Using Machine Learning Algorithms and Spectral Vegetation Indices Derived from UAV Multispectral Imagery

The use of satellite-based Remote Sensing (RS) is a well-developed field of research. RS techniques have been successfully utilized to evaluate the chlorophyll content for the monitoring of sugarcane crops. This research provides a new framework for inferring the chlorophyll content in sugarcane crops at the canopy level using unmanned aerial vehicles (UAVs) and spectral vegetation indices processed with multiple machine learning algorithms. Studies were conducted in a sugarcane field located in Sugarcane Research Institute (SRI, Uda Walawe, Sri Lanka), with various fertilizer applications over the entire growing season from 2020 to 2021. An UAV with multispectral camera was used to collect the aerial images to generate the vegetation indices. Ground measurements of leaf chlorophyll were used as indications for fertilizer status in the sugarcane field. Different machine learning (ML) algorithms were used ground-truthing data of chlorophyll content and spectral vegetation indices to forecast sugarcane chlorophyll content. Several machine learning algorithms such as MLR, RF, DT, SVR, XGB, KNN and ANN were applied in two ways: before feature selection (BFS) by training the algorithms with all twenty-four (24) vegetation indices with five (05) spectral bands and after feature selection (AFS) by training algorithms with fifteen (15) vegetation indices. All the algorithms with both BFS and AFS methods were compared with an estimated coefficient of determination (R2) and root mean square error (RMSE). Spectral indices such as RVI and DVI were shown to be the most reliable indices for estimating chlorophyll content in sugarcane fields, with coefficients of determination (R2) of 0.94 and 0.93, respectively. XGB model shows the highest validation score (R2) and lowest RMSE in both methods of BFS (0.96 and 0.14) and AFS (0.98 and 0.78), respectively. However, KNN and SVR algorithms show the lowest validation accuracy than other models. According to the results, the AFS validation score is higher than BFS in MLR, SVR, XGB and KNN. Even though, validation score of the ANN model is decreased in AFS. The findings demonstrated that the use of multispectral UAV could be utilized to estimate chlorophyll content and measure crop health status over a larger sugarcane field. This methodology will aid in real-time crop nutrition management in sugarcane plantations by reducing the need for conventional measurement of sugarcane chlorophyll content.