PhytoplanktonPhytoplankton (ˌfaɪtoʊˈplæŋktən) are the autotrophic (self-feeding) components of the plankton community and a key part of ocean and freshwater ecosystems. The name comes from the Greek words φυτόν (phyton), meaning 'plant', and πλαγκτός (planktos), meaning 'wanderer' or 'drifter'. Phytoplankton obtain their energy through photosynthesis, as do trees and other plants on land. This means phytoplankton must have light from the sun, so they live in the well-lit surface layers (euphotic zone) of oceans and lakes.
Artificial neural networkArtificial neural networks (ANNs, also shortened to neural networks (NNs) or neural nets) are a branch of machine learning models that are built using principles of neuronal organization discovered by connectionism in the biological neural networks constituting animal brains. An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal to other neurons.
Recurrent neural networkA recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.
Harmful algal bloomA harmful algal bloom (HAB), or excessive algae growth, is an algal bloom that causes negative impacts to other organisms by production of natural algae-produced toxins, mechanical damage to other organisms, or by other means. HABs are sometimes defined as only those algal blooms that produce toxins, and sometimes as any algal bloom that can result in severely lower oxygen levels in natural waters, killing organisms in marine or fresh waters. Blooms can last from a few days to many months.
Neural networkA neural network can refer to a neural circuit of biological neurons (sometimes also called a biological neural network), a network of artificial neurons or nodes in the case of an artificial neural network. Artificial neural networks are used for solving artificial intelligence (AI) problems; they model connections of biological neurons as weights between nodes. A positive weight reflects an excitatory connection, while negative values mean inhibitory connections. All inputs are modified by a weight and summed.
Spring bloomThe spring bloom is a strong increase in phytoplankton abundance (i.e. stock) that typically occurs in the early spring and lasts until late spring or early summer. This seasonal event is characteristic of temperate North Atlantic, sub-polar, and coastal waters. Phytoplankton blooms occur when growth exceeds losses, however there is no universally accepted definition of the magnitude of change or the threshold of abundance that constitutes a bloom. The magnitude, spatial extent and duration of a bloom depends on a variety of abiotic and biotic factors.
CyanotoxinCyanotoxins are toxins produced by cyanobacteria (also known as blue-green algae). Cyanobacteria are found almost everywhere, but particularly in lakes and in the ocean where, under high concentration of phosphorus conditions, they reproduce exponentially to form blooms. Blooming cyanobacteria can produce cyanotoxins in such concentrations that they can poison and even kill animals and humans. Cyanotoxins can also accumulate in other animals such as fish and shellfish, and cause poisonings such as shellfish poisoning.
Types of artificial neural networksThere are many types of artificial neural networks (ANN). Artificial neural networks are computational models inspired by biological neural networks, and are used to approximate functions that are generally unknown. Particularly, they are inspired by the behaviour of neurons and the electrical signals they convey between input (such as from the eyes or nerve endings in the hand), processing, and output from the brain (such as reacting to light, touch, or heat). The way neurons semantically communicate is an area of ongoing research.
Trophic state indexThe Trophic State Index (TSI) is a classification system designed to rate water bodies based on the amount of biological productivity they sustain. Although the term "trophic index" is commonly applied to lakes, any surface water body may be indexed. The TSI of a water body is rated on a scale from zero to one hundred. Under the TSI scale, water bodies may be defined as: oligotrophic (TSI 0–40, having the least amount of biological productivity, "good" water quality); mesotrophic (TSI 40–60, having a moderate level of biological productivity, "fair" water quality); or eutrophic to hypereutrophic (TSI 60–100, having the highest amount of biological productivity, "poor" water quality).
Algal bloomAn algal bloom or algae bloom is a rapid increase or accumulation in the population of algae in freshwater or marine water systems. It is often recognized by the discoloration in the water from the algae's pigments. The term algae encompasses many types of aquatic photosynthetic organisms, both macroscopic multicellular organisms like seaweed and microscopic unicellular organisms like cyanobacteria. Algal bloom commonly refers to the rapid growth of microscopic unicellular algae, not macroscopic algae.
High-nutrient, low-chlorophyll regionsHigh-nutrient, low-chlorophyll (HNLC) regions are regions of the ocean where the abundance of phytoplankton is low and fairly constant despite the availability of macronutrients. Phytoplankton rely on a suite of nutrients for cellular function. Macronutrients (e.g., nitrate, phosphate, silicic acid) are generally available in higher quantities in surface ocean waters, and are the typical components of common garden fertilizers. Micronutrients (e.g., iron, zinc, cobalt) are generally available in lower quantities and include trace metals.
Monomictic lakeMonomictic lakes are holomictic lakes that mix from top to bottom during one mixing period each year. Monomictic lakes may be subdivided into cold and warm types. Cold monomictic lakes are lakes that are covered by ice throughout much of the year. During their brief "summer", the surface waters remain at or below 4 °C. The ice prevents these lakes from mixing in winter. During summer, these lakes lack significant thermal stratification, and they mix thoroughly from top to bottom. These lakes are typical of cold-climate regions (e.
LakeA lake is a naturally occurring, relatively large body of water localized in a basin surrounded by dry land. A lake generally has a slower-moving flow than the inflow or outflow stream(s) that serve to feed or drain it. Lakes lie completely on land and are separate from the ocean, although, like the much larger oceans, they form part of the Earth's water cycle by serving as large standing pools of storage water. Most lakes are freshwater and account for almost all the world's surface freshwater, but some are salt lakes with salinities even higher than that of seawater.
HypolimnionThe hypolimnion or under lake is the dense, bottom layer of water in a thermally-stratified lake. The word "hypolimnion" is derived from λιμνίον. It is the layer that lies below the thermocline. Typically the hypolimnion is the coldest layer of a lake in summer, and the warmest layer during winter. In deep, temperate lakes, the bottom-most waters of the hypolimnion are typically close to 4 °C throughout the year. The hypolimnion may be much warmer in lakes at warmer latitudes.
Lake stratificationLake stratification is the tendency of lakes to form separate and distinct thermal layers during warm weather. Typically stratified lakes show three distinct layers: the epilimnion, comprising the top warm layer; the thermocline (or metalimnion), the middle layer, whose depth may change throughout the day; and the colder hypolimnion, extending to the floor of the lake. Every lake has a set mixing regime that is influenced by lake morphometry and environmental conditions.
Feedforward neural networkA feedforward neural network (FNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. Its flow is uni-directional, meaning that the information in the model flows in only one direction—forward—from the input nodes, through the hidden nodes (if any) and to the output nodes, without any cycles or loops, in contrast to recurrent neural networks, which have a bi-directional flow.
Lake ecosystemA lake ecosystem or lacustrine ecosystem includes biotic (living) plants, animals and micro-organisms, as well as abiotic (non-living) physical and chemical interactions. Lake ecosystems are a prime example of lentic ecosystems (lentic refers to stationary or relatively still freshwater, from the Latin lentus, which means "sluggish"), which include ponds, lakes and wetlands, and much of this article applies to lentic ecosystems in general. Lentic ecosystems can be compared with lotic ecosystems, which involve flowing terrestrial waters such as rivers and streams.
Ocean stratificationOcean stratification is the natural separation of an ocean's water into horizontal layers by density, which is generally stable because warm water floats on top of cold water, and heating is mostly from the sun, which reinforces that arrangement. Stratification is reduced by wind-forced mechanical mixing, but reinforced by convection (warm water rising, cold water sinking). Stratification occurs in all ocean basins and also in other water bodies.
Convolutional neural networkConvolutional neural network (CNN) is a regularized type of feed-forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. For example, for each neuron in the fully-connected layer 10,000 weights would be required for processing an image sized 100 × 100 pixels.
Satellite imagerySatellite images (also Earth observation imagery, spaceborne photography, or simply satellite photo) are s of Earth collected by imaging satellites operated by governments and businesses around the world. Satellite imaging companies sell images by licensing them to governments and businesses such as Apple Maps and Google Maps. The first images from space were taken on sub-orbital flights. The U.S-launched V-2 flight on October 24, 1946, took one image every 1.5 seconds.
